147 accepted papers
Representation Finetuning (ReFT) has recently emerged as an efficient paradigm for adapting pretrained language models by editing hidden representations rather than model weights. However, our preliminary experiments reveal that ReFT is notably more sensitive to training data quality compared to tra
Random frame-level data missing is a critical challenge in multimodal sentiment analysis. Existing methods are largely limited to passive completion via single-pass feedforward connections and static cross-modal fusion, which struggle to generate high-quality completed features. However, the brain i
3D Gaussian Splatting (3DGS) has recently demonstrated significant potential for streaming dynamic scenes, enabling the synthesis of photo-realistic and real-time free-viewpoint videos (FVVs). Conventional streaming pipelines optimize each frame independently, i.e., the attribute of the 3D Gaussians
Code search, framed as information retrieval (IR), underpins modern software engineering and increasingly powers retrieval-augmented generation (RAG), improving code discovery, reuse, and the reliability of LLM-based coding.Yet existing code IR models remain largely text-centric and often overlook t
Reliable reasoning in Large Language Models (LLMs) is challenged by their propensity for hallucination. While augmenting LLMs with Knowledge Graphs (KGs) improves factual accuracy, existing KG-augmented methods fail to quantify epistemic uncertainty in both the retrieved evidence and LLMs' reasoning
The vulnerability of deep neural networks (DNNs) has been preliminarily verified. Existing black-box adversarial attacks usually require multi-round interaction with the model and consume numerous queries, which is impractical in the real-world and hard to scale to recently emerged Video-LLMs. Moreo
Causal softmax attention is the algorithmic foundation of modern large language models. Inspired by linear attention, recent work has sought to enhance it by incorporating forget gates. However, these efforts, such as FoX, have been limited to coarse, scalar gates. While fine-grained, element-wise g…
This paper investigates training better visual world models for robot manipulation, i.e., models that can predict future visual observations by conditioning on past frames and robot actions. Specifically, we consider world models that operate on RGB-D frames (RGB-D world models). As opposed to canon
This paper investigates training better visual world models for robot manipulation, i.e., models that can predict future visual observations by conditioning on past frames and robot actions. Specifically, we consider world models that operate on RGB-D frames (RGB-D world models). As opposed to canon…
Instruction-based image editing through natural language has emerged as a powerful paradigm for intuitive visual manipulation. While recent models achieve impressive results on single edits, they suffer from severe quality degradation under multi-turn editing. Through systematic analysis, we identif
Studies have shown that catastrophic forgetting primarily stems from the difficulty of reactivating old memories; although parameter-efficient fine-tuning can mitigate forgetting while keeping most model parameters frozen, it still falls short in fully reawakening knowledge of prior tasks. In contra…
Abstract visual reasoning benchmarks such as ARC-AGI evaluate the ability to infer generalizable transformation rules from few graphical demonstrations, a capability where current deep learning models severely underperform. Mainstream LLMs achieve only 15.8% (DeepSeek-R1) and 34.5% (o3-mini-high) ac
Large Multimodal Models encode extensive factual knowledge in their pre-trained weights. However, its knowledge remains static and limited, unable to keep pace with real-world developments, which hinders continuous knowledge acquisition. Effective knowledge injection thus becomes critical, involving…
Reasoning-augmented machine learning systems have shown improved performance in various domains, including image generation. However, existing reasoning-based methods for image generation either restrict reasoning to a single modality (image or text) or rely on high-quality reasoning data for fine-t…
Reward design is of great importance for solving complex tasks with reinforcement learning. Recent studies have explored using image-text similarity produced by vision-language models (VLMs) to augment rewards of a task with visual feedback. A common practice linearly adds VLM scores to task or succ…
Sketch-based solutions are widely used to estimate item frequencies in infinite data streams.Traditional hand-crafted sketches face the bottleneck of further eliminating errors because they cannot fully utilize the data stream distribution.Although recent neural sketches represented by MetaSketch an
In DRL, an agent is trained from a stream of experience. In a continual learning setting, such agents can suffer from \emph{plasticity loss}: their ability to learn new skills from new experiences diminishes over training. Recently, Mixture-of-Experts (MoE) networks have been reported to enable scal…
In vision–language models (VLMs), misalignment between textual descriptions and visual coordinates often induces hallucinations. This issue becomes particularly severe in dense prediction tasks such as spatial–temporal video grounding (STVG). Prior approaches typically focus on enhancing visual–text…
Reinforcement Learning with Verifiable Rewards (RLVR) is highly effective for enhancing LLM reasoning, yet recent evidence shows models like Qwen2.5 achieve significant gains even with spurious rewards. We investigate this phenomenon and identify ``Perplexity Paradox'': spurious RLVR triggers a dive…
Vision-language retrieval (VLR), which uses text or image queries to retrieve corresponding cross-modal content, plays a crucial role in multimedia and computer vision tasks. However, challenging concepts in queries often confuse retrievers, limiting their ability to align concepts with visual conte
Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks. However, a major challenge in developing generalized GUI agents is the lack of sufficient trajectory data across various o
Retrieval-Augmented Generation (RAG) systems are increasingly deployed to provide query-based access to large knowledge bases, thereby introducing concrete privacy risks whereby the underlying corpus may be partially or fully extracted through the deployed service. Existing extraction attacks typica…
Large Multimodal Models (LMMs) store vast amounts of pretrained knowledge but struggle to remain aligned with real-world updates, making it difficult to avoid capability degradation when acquiring evolving knowledge. Furthermore, most current work focuses on exploring static textual knowledge inject…
Knowledge Graphs (KGs) have revolutionized structured knowledge representation, yet their capacity to model real-world complexity and heterogeneity remains fundamentally constrained. The emerging paradigm of Multi-View Knowledge Graphs (MVKGs) addresses this gap through multi-view learning, but exis
Can our brain signals faithfully reflect the original visual stimuli, even including high-frequency details? Although human perceptual and cognitive capacities enable us to process and remember visual information, these abilities are constrained by several factors, such as limited attentional resour…
Recent advances in text-to-image personalization have enabled high-quality and controllable image synthesis for user-provided concepts. However, existing methods still struggle to balance identity preservation with text alignment. Our approach is based on the fact that generating prompt-aligned imag…
Open-world reinforcement learning challenges agents to develop intelligent behavior in vast exploration spaces. Recent approaches like LS-Imagine have advanced the field by extending imagination horizons through jumpy state transitions, yet remain limited by fixed exploration mechanisms and static j…
Multimodal Information Extraction (MIE) has gained attention for extracting structured information from multimedia sources. Traditional methods tackle MIE tasks separately, missing opportunities to share knowledge across tasks. Recent approaches unify these tasks into a generation problem using inst
High-quality sentence embeddings are fundamental in many natural language processing (NLP) tasks, such as semantic textual similarity (STS) and retrieval-augmented generation (RAG). However, most existing methods leverage fixed-length sentence embeddings from full-layer language models, which lack t…
The study of enhancing model robustness against adversarial examples has become increasingly critical in the security of deep learning, leading to the development of numerous adversarial defense techniques. While these defense methods have shown promise in mitigating the impact of adversarial pertur…
This paper investigates the problem of understanding dynamic 3D scenes from egocentric observations, a key challenge in robotics and embodied AI. Unlike prior studies that explored this as long-form video understanding and utilized egocentric video only, we instead propose an LLM-based agent, Embodi…
Current dual-fusion models for 6D pose estimation often lead to increased computational complexity and risk of overfitting with the addition of more networks. To address this, we propose a Cross-modal Fusion Network (CFN), which extracts robust dual-modal features while reducing computation energy a…
Vision-language retrieval (VLR) has attracted significant attention in both academia and industry, which involves using text (or images) as queries to retrieve corresponding images (or text). However, existing methods often neglect the rich visual semantics knowledge of entities, thus leading to inc…
Social event detection involves identifying and categorizing important events from social media, which relies on labeled data, but annotation is costly and labor-intensive. To address this problem, we propose Augmentation framework for Social Event Detection (SED-Aug), a plug-and-play dual augmentat…
Visual question generation (VQG) aims to generate questions from images automatically. While existing studies primarily focus on the quality of generated questions, such as fluency and relevance, the difficulty of the questions is also a crucial factor in assessing their quality. Question difficulty…
Removing reflection from a single image is challenging due to the absence of general reflection priors. Although existing methods incorporate extensive user guidance for satisfactory performance, they often lack the flexibility to adapt user guidance in different modalities, and dense user interacti…
Diffusion policies are widely adopted in complex visuomotor tasks for their ability to capture multimodal action distributions. However, the multiple sampling steps required for action generation significantly harm real-time inference efficiency, which limits their applicability in real-time decisio…
Code search aims to quickly locate target code snippets from databases using natural language queries, which promotes code reusability. Existing methods can effectively obtain aligned token-level and query word-level features. However, these studies usually represent the semantics of code and query…
3D visual grounding has made notable progress in localizing objects within complex 3D scenes. However, grounding referring expressions beyond objects in 3D scenes remains unexplored. In this paper, we introduce Anywhere3D-Bench, a holistic 3D visual grounding benchmark consisting of 2,886 referring…
In recent years, large language models (LLMs) have made remarkable advancements, yet hallucination, where models produce inaccurate or non-factual statements, remains a significant challenge for real-world deployment. Although current classification-based methods, such as SAPLMA, are highly efficien…
Warning: This paper contains offensive content that may disturb some readers. Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation r…
Multimodal agents, which integrate a controller (e.g., a vision language model) with external tools, have demonstrated remarkable capabilities in tackling complex multimodal tasks. Existing approaches for training these agents, both supervised fine-tuning and reinforcement learning, depend on extens…
E-commerce authoring entails creating engaging, diverse, and targeted content to enhance preference elicitation and retrieval experience. While Large Language Models (LLMs) have revolutionized content generation, they often fall short in e-commerce applications due to their limited memorization of d…
Estimating normals for noisy point clouds is a persistent challenge in 3D geometry processing, particularly for end-to-end oriented normal estimation. Existing methods generally address relatively clean data and rely on supervised priors to fit local surfaces within specific neighborhoods. In this p…
Motion planning in high-dimensional continuous spaces remains challenging due to complex environments and computational constraints. Although learning-based planners, especially graph neural network (GNN)-based, have significantly improved planning performance, they still struggle with inaccurate gr…
Knowledge editing techniques have emerged as essential tools for updating the factual knowledge of large language models (LLMs) and multimodal models (LMMs), allowing them to correct outdated or inaccurate information without retraining from scratch. However, existing benchmarks for multimodal knowl…
Instruction-following capability has become a major ability to be evaluated for Large Language Models. However, existing datasets, such as IFEval, are either predominantly monolingual and centered on English or simply machine translated to other languages, limiting their applicability in multilingua…
Fast Adversarial Training (FAT) employs the single-step Fast Gradient Sign Method (FGSM) to generate adversarial examples, reducing the computational costs of traditional adversarial training. However, FAT suffers from Catastrophic Overfitting (CO), where models' robust accuracy against multi-step a…
Embodied scene understanding requires not only comprehending visual-spatial information that has been observed but also determining where to explore next in the 3D physical world. Existing 3D Vision-Language (3D-VL) models primarily focus on grounding objects in static observations from 3D reconstru…
The advancement of large language models (LLMs) prompts the development of multi-modal agents, which are used as a controller to call external tools, providing a feasible way to solve practical tasks. In this paper, we propose a multi-modal agent tuning method that automatically generates multi-moda…
Text-guided image editing involves modifying a source image based on a language instruction and, typically, requires changes to only small local regions. However, existing approaches generate the entire target image rather than selectively regenerate only the intended editing areas. This results in…
Recent advances in large language models (LLMs) have demonstrated remarkable potential in the field of natural language processing. Unfortunately, LLMs face significant security and ethical risks. Although techniques such as safety alignment are developed for defense, prior researches reveal the pos…
Large language models (LLMs) excel at complex reasoning tasks but often suffer from overconfidence and computational inefficiency due to fixed computation budgets and miscalibrated confidence estimates. We present a novel framework for computationally efficient, trustworthy reasoning under uncertain
With the growing significance of network security, the classification of encrypted traffic has emerged as an urgent challenge. Traditional byte-based traffic analysis methods are constrained by the rigid granularity of information and fail to fully exploit the diverse correlations between bytes. To…
Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated forget sets. Moreover, these methods perform unlearning at a coarse granularity, often leading to excessive forgetting a…
3D Gaussian Splatting-based indoor open-world free-view synthesis approaches have shown significant performance with dense input images. However, they exhibit poor performance when confronted with sparse inputs, primarily due to the sparse distribution of Gaussian points and insufficient view superv…
Recently, large language models (LLMs) have shown strong potential in facilitating human-robotic interaction and collaboration. However, existing LLM-based systems often overlook the misalignment between human and robot perceptions, which hinders their effective communication and real-world robot de
Manual slide creation is labor-intensive and requires expert prior knowledge. Existing natural language-based LLM generation methods struggle to capture the visual and structural nuances of slide designs. To address this, we formalize the Reference Image to Slide Generation task and propose Slide2Co
Large Reasoning Models (LRMs) demonstrate strong performance on complex tasks through chain-of-thought (CoT) reasoning. However, they suffer from high inference latency due to lengthy reasoning chains. In this paper, we propose SpecCoT, a collaborative framework that combines large and small models
Video advertising has become a popular marketing strategy on e-commerce platforms, requiring high-level semantic reasoning like selling point discovery, narrative organization. Previous rule-based methods struggle with these complex tasks, and learning-based approaches demand large datasets and high
Building autonomous agents that perceive and operate graphical user interfaces (GUIs) like humans has long been a vision in the field of artificial intelligence. Central to these agents is the capability for GUI interaction, which involves GUI understanding and planning capabilities. Existing method…
Existing 3D vision-language (3D-VL) benchmarks fall short in evaluating 3D-VL models, creating a "mist" that obscures rigorous insights into model capabilities and 3D-VL tasks. This mist persists due to three key limitations. First, flawed test data, like ambiguous referential text in the grounding…
3D Gaussian Splatting has recently emerged as an efficient solution for high-quality and real-time novel view synthesis. However, its capability for accurate surface reconstruction remains underexplored. Due to the discrete and unstructured nature of Gaussians, supervision based solely on image rend…
The rapid advancement of vision-language models (VLMs) has brought a lot of attention to their safety alignment. However, existing methods have primarily focused on model undersafety, where the model responds to hazardous queries, while neglecting oversafety, where the model refuses to answer safe q…
Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns. However, the increasing size of these models and their limited access make improving their robustness a cha…
Traditional adversarial training, while effective at improving machine learning model robustness, is computationally intensive. Fast Adversarial Training (FAT) addresses this by using a single-step attack to generate adversarial examples more efficiently. Nonetheless, FAT is susceptible to a phenome…
The incredibly efficient and agile flight abilities of butterflies have become the inspiration for the design of butterfly-inspired flapping-wing robots, but their intricate flight mechanisms bring challenges to the flight control of these robots. Aerodynamic simulation emerges as an effective tool
Leveraging massive knowledge from large language models (LLMs), recent machine learning models show notable successes in general-purpose task solving in diverse domains such as computer vision and robotics. However, several significant challenges remain: (i) most of these models rely on 2D images ye…
In this paper, we develop a multiple-object zooming system which can capture clear images of different objects at an ultrafast speed. The system consists of a panoramic HFR stereo camera and a galvanometer-based reflective pan-tilt-zoom (PTZ) camera. In order to alleviate the impact of brightness, n…
Recent advances in text-to-image models have enabled high-quality personalized image synthesis based on user-provided concepts with flexible textual control. In this work, we analyze the limitations of two primary techniques in text-to-image personalization: Textual Inversion and DreamBooth. When in…
Defect detection is a pivotal aspect ensuring product quality and production efficiency in industrial manufacturing. Existing studies on defect detection predominantly focus on locating defects through bounding boxes and classifying defect types. However, their methods can only provide limited infor…
We introduce Bongard-OpenWorld, a new benchmark for evaluating real-world few-shot reasoning for machine vision. It originates from the classical Bongard Problems (BPs): Given two sets of images (positive and negative), the model needs to identify the set that query images belong to by inducing the…
Utilizing large language models (LLMs) to compose off-the-shelf visual tools represents a promising avenue of research for developing robust visual assistants capable of addressing diverse visual tasks. However these methods often overlook the potential for continual learning typically by freezing t…
Inversion methods, such as Textual Inversion, generate personalized images by incorporating concepts of interest provided by user images. However, existing methods often suffer from overfitting issues, where the dominant presence of inverted concepts leads to the absence of other desired concepts. I…
Recently there has been a surge in face personalization techniques benefiting from the advanced capabilities of pretrained text-to-image diffusion models. Among these a notable method is Textual Inversion which generates personalized images by inverting given images into textual embeddings. However…
In high-stakes sectors such as network security, IoT security, accurately distinguishing between normal and anomalous data is critical due to the significant implications for operational success and safety in decision-making. The complexity is exacerbated by the presence of unlabeled data and the op…
Brain computer interface with time-series physiological signal analysis (e.g., EEG and fNIRS) is commonly-used technology for the auxiliary diagnosis of dementia. However, due to the non-stationary, non-linear and low signal-to-noise ratio of time-series signal, as well as the lack of relevant demen…
Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. NS-RL entails structured state representations for tasks with visual observations, but previous methods cannot refine the str…
Entity alignment (EA) aims to merge two knowledge graphs (KGs) by identifying equivalent entity pairs. While existing methods heavily rely on human-generated labels, it is prohibitively expensive to incorporate cross-domain experts for annotation in real-world scenarios. The advent of Large Language…
Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spon…
Vehicle-to-everything (V2X) is a popular topic in the field of Autonomous Driving in recent years. Vehicle-infrastructure cooperation (VIC) becomes one of the important research area. Due to the complexity of traffic conditions such as blind spots and occlusion it greatly limits the perception capab…
Current learning models often struggle with human-like systematic generalization, particularly in learning compositional rules from limited data and extrapolating them to novel combinations. We introduce the Neural-Symbolic Recursive Ma- chine ( NSR), whose core is a Grounded Symbol System ( GSS), a…
This paper presents OmniJARVIS, a novel Vision-Language-Action (VLA) model for open-world instruction-following agents in Minecraft. Compared to prior works that either emit textual goals to separate controllers or produce the control command directly, OmniJARVIS seeks a different path to ensure bot…
Weight quantization is an effective technique to compress deep neural networks for their deployment on edge devices with limited resources. Traditional loss-aware quantization methods commonly use the quantized gradient to replace the full-precision gradient. However, we discover that the gradient e…
Finetuning large language models (LLMs) has been empirically effective on a variety of downstream tasks. Existing approaches to finetuning an LLM either focus on parameter-efficient finetuning, which only updates a small number of trainable parameters, or attempt to reduce the memory footprint durin…
Large vision-language models (LVLMs) have made significant progress in recent years. While LVLMs exhibit excellent ability in language understanding, question answering, and conversations of visual inputs, they are prone to producing hallucinations. While several methods are proposed to evaluate the…
Building Non-autoregressive (NAR) models in image captioning can fundamentally tackle the high inference latency of autoregressive models. However, existing NAR image captioning models are trained on maximum likelihood estimation, and suffer from their inherent multi-modality problem. Although const…
"3D vision-language (3dvl) grounding, which aims to align language with 3D physical environments, stands as a cornerstone in developing embodied agents. In comparison to recent advancements in the 2D domain, grounding language in 3D scenes faces two significant challenges: (i) the scarcity of paired…
This paper presents UltraEdit, a large-scale (~ 4M editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like InstructPix2Pix and MagicBrush, and provide a *systematic* approach to producing…
3D vision-language grounding (3D-VL) is an emerging field that aims to connect the 3D physical world with natural language, which is crucial for achieving embodied intelligence. Current 3D-VL models rely heavily on sophisticated modules, auxiliary losses, and optimization tricks, which calls for a s…
Inspired by humans' exceptional ability to master arithmetic and generalize to new problems, we present a new dataset, HINT, to examine machines' capability of learning generalizable concepts at three levels: perception, syntax, and semantics. In HINT, machines are tasked with learning how concepts…
Abstract Meaning Representation (AMR) is a semantic representation that can enhance natural language generation (NLG) by providing a logical semantic input. In this paper, we propose the AMR-TST, an AMR-based text style transfer (TST) technique. The AMR-TST converts the source text to an AMR graph a…
Diffusion models, as a novel generative paradigm, have achieved remarkable success in various image generation tasks such as image inpainting, image-to-text translation, and video generation. Graph generation is a crucial computational task on graphs with numerous real-world applications. It aims to…
Many security applications require unsupervised anomaly detection, as malicious data are extremely rare and often only unlabeled normal data are available for training (i.e., zero-positive). However, security operators are concerned about the high stakes of trusting black-box models due to their lac…
Multimodal named entity recognition (MNER) and multimodal relation extraction (MRE) are two fundamental subtasks in the multimodal knowledge graph construction task. However, the existing methods usually handle two tasks independently, which ignores the bidirectional interaction between them. This p…
Conventional imitation learning assumes access to the actions of demonstrators, but these motor signals are often non-observable in naturalistic settings. Additionally, sequential decision-making behaviors in these settings can deviate from the assumptions of a standard Markov Decision Process (MDP)…
Regular expressions (REs) offer one-shot solutions for many networking tasks, e.g., network intrusion detection. However, REs purely rely on expert knowledge and cannot utilize labeled data for better accuracy. Today, neural networks (NNs) have shown superior accuracy and flexibility, thanks to thei…
Normal estimation for 3D point clouds is a fundamental task in 3D geometry processing. The state-of-the-art methods rely on priors of fitting local surfaces learned from normal supervision. However, normal supervision in benchmarks comes from synthetic shapes and is usually not available from real s…
Self-attention-based models have achieved remarkable progress in short-text mining. However, the quadratic computational complexities restrict their application in long text processing. Prior works have adopted the chunking strategy to divide long documents into chunks and stack a self-attention bac…
We revisit the multimodal entity and relation extraction from a translation point of view. Special attention is paid on the misalignment issue in text-image datasets which may mislead the learning. We are motivated by the fact that the cross-modal misalignment is a similar problem of cross-lingual d…
We propose a novel method called SHS-Net for oriented normal estimation of point clouds by learning signed hyper surfaces, which can accurately predict normals with global consistent orientation from various point clouds. Almost all existing methods estimate oriented normals through a two-stage pipe…
We propose a new task to benchmark scene understanding of embodied agents: Situated Question Answering in 3D Scenes (SQA3D). Given a scene context (e.g., 3D scan), SQA3D requires the tested agent to first understand its situation (position, orientation, etc.) in the 3D scene as described by text, th…
Computer end users have spent billions of hours completing daily tasks like tabular data processing and project timeline scheduling. Most of these tasks are repetitive and error-prone, yet most end users lack the skill to automate these burdensome works. With the advent of large language models (LLM…
Heterogeneous graphs are ubiquitous to model complex data. There are urgent needs on powerful heterogeneous graph neural networks to effectively support important applications. We identify a potential semantic mixing issue in existing message passing processes, where the representations of the neigh…
Traditional gimbal-based bionic eye systems usually use a multi-degree-of-freedom mechanical platform to move the camera freely, which makes the structure complex and bulky. The galvanometer-based reflective bionic eye system uses a galvanometer to replace the traditional mechanical rotation structu…
While the deep learning-based image deraining methods have made great progress in recent years, there are two major shortcomings in their application in real-world situations. Firstly, the gap between the low-level vision task represented by rain removal and the high-level vision task represented by
Despite a surge of recent advances in promoting machine Learning (ML) fairness, the existing mainstream approaches mostly require training or finetuning the entire weights of the neural network to meet the fairness criteria. However, this is often infeasible in practice for those large-scale traine…
Depth completion aims to recover dense depth maps from sparse depth maps using the corresponding RGB images as guides. Learning guided convolutional network (GuideNet) is one of the state-of-the-art (SoTA) depth completion methods. In this letter, we propose a robust and efficient end-to-end guided
We propose a novel normal estimation method called HSurf-Net, which can accurately predict normals from point clouds with noise and density variations. Previous methods focus on learning point weights to fit neighborhoods into a geometric surface approximated by a polynomial function with a predefin…
Initially developed for natural language processing (NLP), Transformer model is now widely used for speech processing tasks such as speaker recognition, due to its powerful sequence modeling capabilities. However, conventional self-attention mechanisms are originally designed for modeling textual se…
Measurement rates for both targets and clutter have been assumed to be known a priori in most existing tracking systems, whereas practically the rates may be unknown to users or time-varying. This paper therefore fills this gap by developing a Poisson mixture process tracker (PMPT) to capture the te…
Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists…
In finance, the risk of an entity depends not only on its historical information but also on the risk propagated by its related peers. Pilot studies rely on Graph Neural Networks (GNNs) to model this risk propagation, where each entity is treated as a node and represented by its time-series inform…
Active learning (AL) is a subfield of machine learning (ML) in which a learning algorithm aims to achieve good accuracy with fewer training samples by interactively querying the oracles to label new data points. Pool-based AL is well-motivated in many ML tasks, where unlabeled data is abundant, but…
Unsupervised text style transfer aims to alter the underlying style of the text to a desired value while keeping its style-independent semantics, without the support of parallel training corpora. Existing methods struggle to achieve both high style conversion rate and low content loss, exhibiting th…
Transparent objects with unique visual properties often make depth cameras fail to scan their reflective and refractive surfaces. Recent studies on depth completion of transparent objects have leveraged a linear system based on the geometric constraints to predict the missing depth, which is hard to…
Question generation is a challenging task and has attracted widespread attention in recent years. Although previous studies have made great progress, there are still two main shortcomings: First, previous work did not simultaneously capture the sequence information and structure information hidden i…
In this paper, we explore Non-AutoRegressive (NAR) decoding for unsupervised text style transfer. We first propose a base NAR model by directly adapting the common training scheme from its AutoRegressive (AR) counterpart. Despite the faster inference speed over the AR model, this NAR model sacrifice…
Previous neural solvers of math word problems (MWPs) are learned with full supervision and fail to generate diverse solutions. In this paper, we address this issue by introducing a weakly-supervised paradigm for learning MWPs. Our method only requires the annotations of the final answers and can gen…
Currently, text classification studies mainly focus on training classifiers by using textual input only, or enhancing semantic features by introducing external knowledge (e.g., hand-craft lexicons and domain knowledge). In contrast, some intrinsic statistical features of the corpus, like word freque…
In finance, the momentum spillovers of listed firms is well acknowledged. Only few studies predicted the trend of one firm in terms of its relevant firms. A common strategy of the pilot work is to adopt graph convolution networks (GCNs) with some predefined firm relations. However, momentum spillove…
Solving algebra story problems remains a challenging task in artificial intelligence, which requires a detailed understanding of real-world situations and a strong mathematical reasoning capability. Previous neural solvers of math word problems directly translate problem texts into equations, lackin…
As an interesting and challenging task, story ending generation aims at generating a reasonable and coherent ending for a given story context. The key challenge of the task is to comprehend the context sufficiently and capture the hidden logic information effectively, which has not been well explore…
This paper proposes the first tracklet proposal network, named PC-TCNN, for Multi-Object Tracking (MOT) on point clouds. Our pipeline first generates tracklet proposals, then refines these tracklets and associates them to generate long trajectories. Specifically, object proposal generation and moti…
Cognitive grammar suggests that the acquisition of language grammar is grounded within visual structures. While grammar is an essential representation of natural language, it also exists ubiquitously in vision to represent the hierarchical part-whole structure. In this work, we study grounded gramma…
We study the machine's understanding of embodied reference: One agent uses both language and gesture to refer to an object to another agent in a shared physical environment. Of note, this new visual task requires understanding multimodal cues with perspective-taking to identify which object is being…
Humans can progressively learn visual concepts from easy to hard questions. To mimic this efficient learning ability, we propose a competence-aware curriculum for visual concept learning in a question-answering manner. Specifically, we design a neural-symbolic concept learner for learning the visual…
Relation Classification (RC) plays an important role in natural language processing (NLP). Current conventional supervised and distantly supervised RC models always make a closed-world assumption which ignores the emergence of novel relations in open environment. To incrementally recognize the novel…
Emotion-cause pair extraction (ECPE) aims at extracting emotions and causes as pairs from documents, where each pair contains an emotion clause and a set of cause clauses. Existing approaches address the task by first extracting emotion and cause clauses via two binary classifiers separately, and th…
Discriminating pathologic cognitive decline from the expected decline of normal aging is an important research topic for elderly care and health monitoring. However, most cognitive assessment methods only work when data distributions of the training set and testing set are consistent. Enabling exist…
The goal of neural-symbolic computation is to integrate the connectionist and symbolist paradigms. Prior methods learn the neural-symbolic models using reinforcement learning (RL) approaches, which ignore the error propagation in the symbolic reasoning module and thus converge slowly with sparse rew…
Entities are the major proportion and build up the topic of text summaries. Although existing text summarization models can produce promising results of automatic metrics, for example, ROUGE, it is difficult to guarantee that an entity is contained in generated summaries. In this paper, we propose a…
Gait recognition, applied to identify individual walking patterns in a long-distance, is one of the most promising video-based biometric technologies. At present, most gait recognition methods take the whole human body as a unit to establish the spatio-temporal representations. However, we have obse…
In group object tracking, the identification of the group leader can be highly beneficial for predicting the intention and future manoeuvres of objects as well as learning the underlying group behaviour traits. This paper presents an online approach for inferring dominant entities in tracked groups…
Speaker verification aims to recognize target speakers with very few enrollment utterances. Conventional approaches learn a representation model to extract the speaker embeddings for verification. Recently, there are several new approaches in meta-learning which try to learn a shared metric space. A…
Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. To suppressing the impact of mislabeled data, this paper proposes a conceptually simple yet efficient training block, termed as Attentive Feature Mixup (AFM), which allows pay…
We present a novel deep convolutional network pipeline, LO-Net, for real-time lidar odometry estimation. Unlike most existing lidar odometry (LO) estimations that go through individually designed feature selection, feature matching, and pose estimation pipeline, LO-Net can be trained in an end-to-en…
Reinforcement learning is a framework to make sequential decisions. The combination with deep neural networks further improves the ability of this framework. Convolutional nerual networks make it possible to make sequential decisions based on raw pixels information directly and make reinforcement le…
We introduce the first visual privacy dataset originating from people who are blind in order to better understand their privacy disclosures and to encourage the development of algorithms that can assist in preventing their unintended disclosures. It includes 8,862 regions showing private content ac…
Visual question answering is the task of returning the answer to a question about an image. A challenge is that different people often provide different answers to the same visual question. To our knowledge, this is the first work that aims to understand why. We propose a taxonomy of nine plausible…
Most of the proposed person re-identification algorithms conduct supervised training and testing on single labeled datasets with small size, so directly deploying these trained models to a large-scale real-world camera network may lead to poor performance due to underfitting. It is challenging to in…
Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even more importance compared with the answer itself, since it makes the question an…
The study of algorithms to automatically answer visual questions currently is motivated by visual question answering (VQA) datasets constructed in artificial VQA settings. We propose VizWiz, the first goal-oriented VQA dataset arising from a natural VQA setting. VizWiz consists of 31,000 visual qu…
Face Super Resolution(FSR) is to infer High Resolution(HR) facial images from given Low Resolution(LR) ones with the assistance of LR and HR training pairs. Among existing methods, local patch based methods are superior in visual and objective quality than global based methods. These local patch bas…
Unsupervised learning with generative adversarial networks (GANs) has proven hugely successful. Regular GANs hypothesize the discriminator as a classifier with the sigmoid cross entropy loss function. However, we found that this loss function may lead to the vanishing gradients problem during the le…
Texture classification has been extensively studied in computer vision. Recent research shows that the combination of Fisher vector (FV) encoding and convolutional neural network (CNN) provides significant improvement in texture classification over the previous feature representation methods. Howeve…
Texture, as a fundamental characteristic of objects, has attracted much attention in computer vision research. Performance of texture classification is however still lacking for some challenging cases, largely due to the high intra-class variation and low inter-class distinction. To tackle these iss…