119 accepted papers
Pre-trained Vision Transformer (ViT) models have achieved impressive performance across various computer vision tasks. However, most existing pre-trained models are built on fixed datasets and lack the flexibility to incorporate new pre-training data. When additional data becomes available, previous
Active recognition, a fundamental task in embodied vision, aims to improve recognition performance by dynamically adjusting viewpoints and poses to mitigate the negative impacts of occlusion and blind spots. Although existing active recognition methods possess basic viewpoint adaptation capabilities
As a foundational task in human-centric cross-modal intelligence, motion-language retrieval aims to bridge the semantic gap between natural language and human motion, enabling intuitive motion analysis, yet existing approaches predominantly focus on aligning entire motion sequences with global textu…
Text-to-image (T2I) diffusion models effectively produce semantically aligned images, but their reliance on training distributions constrains their capacity for synthesizing truly novel, out-of-distribution concepts. Existing methods attempt to enhance creativity through semantic exploration, such a
Chain-of-Thought (CoT) prompting has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing implementations, such as in-context learning and fine-tuning, remain costly and inefficient. To improve CoT reasoning at a lower cost, and in…
Cloud-Edge Continual Test-Time Adaptation (CTTA)--with edge devices processing real-time data and the cloud offering strong computing power--is a critical paradigm for models that adapt to dynamic data distributions in real-world scenarios. However, most existing frameworks assume architectural homo
Continual Test-Time Domain Adaptation (CTTA) aims to adapt a pre-trained source model to a dynamically evolving target domain without requiring additional data collection or labeling efforts. A key challenge in this setting is to achieve rapid performance improvement in the current domain using unla
In-context learning (ICL) has emerged as a powerful paradigm for Large Visual Language Models (LVLMs), enabling them to leverage a few examples directly from input contexts. However, the effectiveness of this approach is heavily reliant on the selection of demonstrations, a process that is NP-hard.
CLIP (Contrastive Language-Image Pre-training) has attracted widespread attention for its multimodal generalizable knowledge, which is significant for downstream tasks. However, the computational overhead of a large number of parameters and large-scale pre-training poses challenges of pre-training a
Fine-tuning large language models for vertical domains remains a labor-intensive and expensive process, requiring domain experts to curate data, configure training, and iteratively diagnose model behavior. Despite growing interest in autonomous machine learning, no prior work has tackled end-to-end …
Speculative Decoding (SD) is a key technique for accelerating Large Language Model (LLM) inference, but it typically requires training a draft model on a large dataset. We approach this problem from a data-centric perspective, finding that not all training samples contribute equally to the SD accept…
Floorplan localization aims to estimate the camera pose of a query image with respect to a 2D floorplan, providing a lightweight and long-term stable alternative to localization based on 3D maps or large image databases for indoor robotics and AR. Recent methods frame the problem as ray-based matchi
In the realm of multi-agent systems, the challenge of partial observability is a critical barrier to effective coordination and decision-making. Existing approaches, such as belief state estimation and inter-agent communication, often fall short. Belief-based methods are limited by their focus on pa…
In-context learning (ICL) enhances large language models (LLMs) by incorporating demonstration examples, yet its effectiveness heavily depends on the quality of selected examples. Current methods typically use text embeddings to measure semantic similarity, which often introduces bias in multi-step
Large language models (LLMs) have demonstrated remarkable generalization across diverse tasks, suggesting the existence of task-agnostic, generalizable knowledge encoded within them. However, how to systematically extract and evaluate this knowledge remains unexplored. In this work, we innovatively…
Biological intelligence has driven significant progress in artificial intelligence (AI), but a critical gap remains: biological systems inherit innate abilities from genes, with brains initialized by blueprints refined over 3.5 billion years of evolution, while machines rely heavily on inefficient,
This paper pays attention to open-vocabulary 3D object affordance grounding (OVAG), which aims to localize affordance regions on 3D objects by leveraging interaction images or textual instructions. Most existing methods treat interaction images as sources of external affordance knowledge and align t…
Evaluating the robustness of Large Vision-Language Models (LVLMs) is essential for their continued development and responsible deployment in real-world applications. However, existing robustness benchmarks typically focus on hallucination or misleading textual inputs, while largely overlooking the e…
Memory is a core capability of autonomous agents, yet existing benchmarks evaluate it primarily in constrained settings such as short dialogues or synthetic tasks, failing to reflect realistic agent deployments. We present \textbf{Memoria-Bench}, a benchmark for evaluating agent memory grounded in c…
The Segment Anything Model 2 (SAM2) has established a new benchmark for high-precision image and video segmentation, offering significant potential for a wide range of computer vision tasks. Despite its impressive performance, the model
The development of affective multimodal language models (MLMs) has long been constrained by a gap between low-level perception and high-level interaction, leading to fragmented affective capabilities and limited generalization. To bridge this gap, we propose a cognitively inspired three-level hierar
Preference-based reinforcement learning (PbRL) can help avoid sophisticated reward designs and align better with human intentions, showing great promise in various real-world applications. However, obtaining human feedback for preferences can be expensive and time-consuming, which forms a strong bar…
In this work, we present a simple yet theoretically motivated improvement to Supervised Fine-Tuning (SFT) for the Large Language Model (LLM), addressing its limited generalization compared to reinforcement learning (RL). Through mathematical analysis, we reveal that standard SFT gradients implicitly…
Diffusion policy has shown impressive performance in robotic manipulation tasks while struggling with out-of-distribution shifts and limited demonstrations. Recent advances primarily focus on improving geometric or perceptual representations for diffusion policy. However, these approaches rely heavi
Trajectory prediction is critical for autonomous driving, enabling safe and efficient planning in dense, dynamic traffic. Most existing methods optimize prediction accuracy under fixed-length observations. However, real-world driving often yields variable-length, incomplete observations, posing a ch
Model ensembling is a well-established technique for improving the performance of machine learning models. Conventionally, this involves averaging the output distributions of multiple models and selecting the most probable label. This idea has been naturally extended to large language models (LLMs),…
This paper presents a hierarchical control framework for quadrupedal locomotion that unifies the complementary strengths of model-based optimization and reinforcement learning. We develop a convex Quadratic Programming~(QP) solver based on the primal-dual Chambolle-Pock algorithm, enabling both mass…
The KV cache in self-attention has emerged as a major bottleneck in long-context and large-batch inference for LLMs. Existing approaches often treat sparsity prediction and compression as separate modules—relying on auxiliary index structures to select relevant tokens, and on complex quantization sc
Rectified flow models have shown strong potential in high-fidelity video generation, yet extending them to high-resolution remains challenging due to the high cost of full attention and error accumulation in the ODE-solving process. In this paper, we propose S^2Flow, a training-free framework that e
Video highlight detection aims to identify the most engaging segments in long-form videos, supporting content editing and recommendation, especially for movies and TV dramas. However, existing methods are ill-suited to cinematic content due to its narrative complexity, while the scarcity of annotate
Autonomous post-fall recovery is a key bottleneck for long-duration deployment of legged robots, yet prevailing methods depend on flat-ground target poses and heuristic rewards and thus fail to generalize under irregular terrain and random initial states. We introduce a teacher-guided, terrain-aware
Visual Place Recognition (VPR) is a key technology in autonomous driving, robotics, and augmented reality, requiring efficient and robust localization in large-scale environments. However, most existing methods rely on heavy deep models that are computationally expensive and difficult to deploy on e…
Supervised fine-tuning (SFT) is computationally efficient but often yields inferior generalization compared to reinforcement learning (RL). This gap is primarily driven by RL’s use of on-policy data. We propose a framework to bridge this chasm by enabling On-Policy SFT. We first present ***Distribut…
Continual test-time adaptation (CTTA) enables online model adjustment under dynamic distribution shifts in real-world environments. However, most existing CTTA frameworks adopt fixed model architectures, lacking the structural flexibility required for deployment across heterogeneous edge devices wit
Video inpainting aims to restore missing regions while preserving spatial and temporal coherence. Diffusion-based methods achieve strong per-frame reconstruction, but their sampling implicitly generates temporally coupled latent trajectories whose long-horizon stability is not explicitly modeled, le…
Large language models (LLMs) with Mixture-of-Experts (MoE) architectures achieve strong performance under sparse activation. However, their expertise is often fragmented across experts and redundant across layers. Prior studies primarily diagnosed redundancy or parameter importance, revealing overla…
Layer pruning efficiently reduces Large Language Model (LLM) computational costs but often triggers sudden performance collapse. Existing representation-based analyses struggle to explain this mechanism. We propose studying pruning through decision representation. Focusing on multiple-choice tasks, …
Text-conditioned human motion in-betweening leverages keyframes for spatio-temporal control, with text providing high-level semantic guidance for the transitions. However, existing methods are unable to establish a coherent alignment between textual semantics and the spatio-temporal constraints prov
Mixture-of-Experts (MoE) language models organize knowledge into explicitly routed expert modules, making expert-level representations traceable and analyzable. By analyzing expert activation patterns in MoE language large models (LLMs), we find that a subset of experts is consistently activated acr…
Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional attention and cannot directly benefit from the standard key-value (KV) cache as autoregressive models (ARMs) do. To tackle…
View missing remains a significant challenge in graph-based multi-view semi-supervised learning, hindering their real-world applications. To address this issue, traditional methods introduce a missing indicator matrix and focus on mining partial structure among existing samples in each view for labe…
Selecting a compact subset of visual instruction–following data has emerged as an effective way to align large multimodal models with human intentions while avoiding the high cost of full-dataset training. Yet we observe that both full-data training and existing state-of-the-art data selection metho…
Co-speech gesture video generation aims to synthesize realistic, audio-aligned videos of speakers, complete with synchronized facial expressions and body gestures. This task presents challenges due to the significant one-to-many mapping between audio and visual content, further complicated by the sc…
Hallucinations in Large Vision-Language Models (LVLMs) significantly undermine their reliability, motivating researchers to explore the causes of hallucination. However, most studies primarily focus on the language aspect rather than the visual. In this paper, we address how LVLMs process visual inf…
Continual learning from unlabeled data streams while effectively combating catastrophic forgetting poses an intractable challenge. Traditional methods predominantly rely on visual clustering techniques to generate pseudo labels, which are frequently plagued by problems such as noise and suboptimal q…
Wheeled-legged robots combine the efficiency of wheels with the versatility of legs, but face significant energy optimization challenges when navigating diverse environments. In this work, we present a hierarchical control framework that integrates predictive power modeling with residual reinforceme
Large Language Model (LLM) collaborative decoding techniques improve output quality by combining the outputs of multiple models at each generation step, but they incur high computational costs. In this paper, we introduce **Collaborative decoding via Speculation (CoS)**, a novel framework that accel…
The Transformer architecture serves as the foundation of modern AI systems, powering recent advances in Large Language Models (LLMs) and Large Multimodal Models (LMMs). Central to these models, attention mechanisms capture contextual dependencies via token interactions. Beyond inference, attention h…
Automatic inspection of X-ray scans is a critical component of modern safety protocols. It plays an indispensable role in detecting concealed weapons, explosives, and other prohibited items that could pose a threat to public safety. Current surveillance systems perform poorly without human intervent…
In practical applications, it is often necessary to transfer knowledge from large pretrained models to small ones with various architectures for tackling different tasks. The Learngene framework, proposed recently, firstly extracts one compact module termed as learngene from a large well-trained mod…
Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing tasks remains under-explored. In this paper, We introduce KRIS-B…
Appropriate parameter initialization strategies are essential for reducing the high computational costs of training large pretrained models in various task scenarios. Graph HyperNetwork (GHN), a parameter initialization method, has recently demonstrated strong performance in initializing models. How…
Recently, In-context Learning (ICL) has become a significant inference paradigm in Large Multimodal Models (LMMs), utilizing a few in-context demonstrations (ICDs) to prompt LMMs for new tasks. However, the synergistic effects in multimodal data increase the sensitivity of ICL performance to the con…
Video Large Language Models (Vid-LLMs) have made remarkable advancements in comprehending video content for QA dialogue. However, they struggle to extend this visual understanding to tasks requiring precise temporal localization, known as Video Temporal Grounding (VTG). To address this, we introduce…
Audio-driven talking face synthesis (TFS) enables the creation of realistic speaking videos by combining a single facial image with a speech audio clip. Unlike other facial features that naturally deform during speech, teeth represent unique rigid structures whose shape and size should remain consta
Segment Anything Model 2 (SAM2) is a new-generation, high-precision model for image and video segmentation, offering extensive application prospects across numerous computer vision fields. However, as a large-scale model, its huge memory demands and expansive computing costs pose challenges for prac
Financial markets pose fundamental challenges for asset return prediction due to their high dimensionality, non-stationarity, and persistent volatility. Despite advances in large language models and multi-agent systems, current quantitative research pipelines suffer from limited automation, weak int…
This paper addresses the scarcity of low-cost but high-dexterity platforms for collecting real-world multi-fingered robot manipulation data towards generalist robot autonomy. To achieve it, we propose the RAPID Hand, a co-optimized hardware and software platform where the compact 20-DoF hand, robus…
Creative remains an inherently abstract concept for both humans and diffusion models. While text-to-image (T2I) diffusion models can easily generate out-of-distribution concepts like "a blue banana", they struggle with generating combinatorial objects such as "a creative mixture that resembles a let…
Large Language Models (LLMs) show strong performance in natural language processing tasks, but their application in the financial domain is limited. Current methods rely on large datasets and manual prompt engineering, resulting in high data demands, long inference times, and frequent hallucinations…
Spiking Neural Networks (SNNs), inspired by the behavior of biological neurons, have gained significant research interest for resource-constrained edge devices and neuromorphic hardware due to their use of binary spike signals for inter-unit communication with low power consumption. However, the abs
With the growing interest in embodied and spatial intelligence, accurately predicting trajectories in 3D environments has become increasingly critical. However, no datasets have been explicitly designed to study 3D trajectory prediction. To this end, we contribute a 3D motion trajectory (3DMoTraj) d…
Text-to-image diffusion models have achieved remarkable success in generating photorealistic images. However, the inclusion of sensitive information during pre-training poses significant risks. Machine Unlearning (MU) offers a promising solution to eliminate sensitive concepts from these models. Des…
The demand for producing short-form videos for sharing on social media platforms has experienced significant growth in recent times. Despite notable advancements in the fields of video summarization and highlight detection, which can create partially usable short films from raw videos, these approac…
Continual test-time domain adaptation (CTTA) aims to adapt the source pre-trained model to a continually changing target domain without additional data acquisition or labeling costs. This issue necessitates an initial performance enhancement within the present domain without labels while concurrentl…
Data-driven decision-making processes increasingly utilize end-to-end learnable deep neural networks to render final decisions. Sometimes, the output of the forward functions in certain layers is determined by the solutions to mathematical optimization problems, leading to the emergence of different…
Recently, Stitchable Neural Networks (SN-Net) is proposed to stitch some pre-trained networks for quickly building numerous networks with different complexity and performance trade-offs. In this way, the burdens of designing or training the variable-sized networks, which can be used in application s…
This work presents a compact, cumulative, and coalescible probabilistic voxel mapping method to enhance performance, accuracy, and memory efficiency in LiDAR odometry. Probabilistic voxel mapping requires storing past point clouds and re-iterating them to update the uncertainty at every iteration, w…
In recent years, the merging of vast datasets with powerful computational resources has led to the emergence of large pre-trained models in the field of deep learning. However, the common practices often overgeneralize the applicability of these models, overlooking the task-specific resource constra…
Spiking Graph Neural Networks are emerging tools for analyzing graph data along with low energy consumption and certain biological fidelity. Existing methods directly integrate same-reactive spiking neurons into graph neural networks for processing propagated graphs. However, such same-reactive neur…
Weakly supervised natural language video localization (WS-NLVL) aims to retrieve the moment corresponding to a language query in a video with only video-language pairs utilized during training. Despite great success, existing WS-NLVL methods seldomly consider the complex temporal relations enclosing…
In practice, we usually need to build variable-sized models adapting for diverse resource constraints in different application scenarios, where weight initialization is an important step prior to training. The Learngene framework, introduced recently, firstly learns one compact part termed as learng…
Inspired by the success of Large Language Models in dealing with new tasks via In-Context Learning (ICL) in NLP researchers have also developed Large Vision-Language Models (LVLMs) with ICL capabilities. However when implementing ICL using these LVLMs researchers usually resort to the simplest way l…
In practical scenarios, it is necessary to build variable-sized models to accommodate diverse resource constraints, where weight initialization serves as a crucial step preceding training. The recently introduced Learngene framework firstly learns one compact module, termed learngene, from a large w…
As language models continue to scale, Large Language Models (LLMs) have exhibited emerging capabilities in In-Context Learning (ICL), enabling them to solve language tasks by prefixing a few in-context demonstrations (ICDs) as context. Inspired by these advancements, researchers have extended these…
As Archimedes famously said, ``Give me a lever long enough and a fulcrum on which to place it, and I shall move the world'', in this study, we propose to use a tiny Language Model (LM), \eg, a Transformer with 67M parameters, to lever much larger Vision-Language Models (LVLMs) with 9B parameters. Sp…
Vision Transformers (ViTs) are widely used in a variety of applications, while they usually have a fixed architecture that may not match the varying computational resources of different deployment environments. Thus, it is necessary to adapt ViT architectures to devices with diverse computational ov…
Long-tail class incremental learning (LT-CIL) is designed to perpetually acquire novel knowledge from an imbalanced and perpetually evolving data stream while ensuring the retention of previously acquired knowledge. The existing method only re-balances data distribution and ignores exploring the pot…
Image-goal navigation is a challenging task that requires an agent to navigate to a goal indicated by an image in unfamiliar environments. Existing methods utilizing diverse scene memories suffer from inefficient exploration since they use all historical observations for decision-making without cons…
This paper introduces AMT, an \textbf{A}dversarial \textbf{M}eta-\textbf{T}uning methodology, to boost the robust generalization of pre-trained models in the out-of-domain (OOD) few-shot learning. To address the challenge of transferring knowledge from source domains to unseen target domains, we con…
Continual test-time domain adaptation seeks to adapt the source pre-trained model to a continually changing target domain without incurring additional data acquisition or labeling costs. Unfortunately, existing mainstream methods may result in a detrimental cycle. This is attributed to noisy pseudo-…
Pre-trained vision transformers have revolutionized few-shot image classification, and it has been recently demonstrated that the previous common practice of meta-learning in synergy with these pre-trained transformers still holds significance. In this work, we design a new framework centered exclus…
Image-based virtual try-on is an increasingly important task for online shopping. It aims to synthesize images of a specific person wearing a specified garment. Diffusion model-based approaches have recently become popular as they are excellent at image synthesis tasks. However these approaches usua…
We propose expanding the shared Transformer module to produce and initialize Transformers of varying depths, enabling adaptation to diverse resource constraints. Drawing an analogy to genetic expansibility, we term such module as learngene. To identify the expansion mechanism, we delve into the rela…
Open-Set Source-Free Domain Adaptation aims to transfer knowledge in realistic scenarios where the target domain has additional unknown classes compared to the limited-access source domain. Due to the absence of information on unknown classes existing methods mainly transfer knowledge of known class…
This paper addresses the scarcity of large-scale datasets for accurate object-in-hand pose estimation, which is crucial for robotic in-hand manipulation within the "Perception-Planning-Control" paradigm. Specifically, we introduce VinT-6D, the first extensive multi-modal dataset integrating vision,…
Deep learning has advanced through the combination of large datasets and computational power, leading to the development of extensive pre-trained models like Vision Transformers (ViTs). However, these models often assume a one-size-fits-all utility, lacking the ability to initialize models with elas…
After discovering that Language Models (LMs) can be good in-context few-shot learners, numerous strategies have been proposed to optimize in-context sequence configurations. Recently, researchers in Vision-Language (VL) domains also develop their few-shot learners, while they only use the simplest w…
Convolutional neural networks have shown excellent potential on establishing correspondences from 2D images to 3D objects for object 6D pose estimation, both for dense and sparse methods. However, only single geometric representation between each object pixel and keypoint is utilized in existing spa
Continual test-time domain adaptation aims to adapt a source pre-trained model to a continually changing target domain without using any source data. Unfortunately, existing methods based on pseudo-label learning suffer from the changing target domain environment, and the quality of generated pseudo…
Since the advent of knowledge distillation, many researchers have been intrigued by the $\textit{dark knowledge}$ hidden in the soft labels generated by the teacher model. This prompts us to scrutinize the circumstances under which these soft labels are effective. Predominant existing theories impli…
In a video, an object usually appears as the trajectory, i.e., it spans over a few spatial but longer temporal patches, that contains abundant spatiotemporal contexts. However, modern Video-Language BERTs (VDL-BERTs) neglect this trajectory characteristic that they usually follow image-language BERT…
We propose to TransForm Scene Graphs into more descriptive Captions (TFSGC). In TFSGC, we apply multi-head attention (MHA) to design the Graph Neural Network (GNN) for embedding scene graphs. After embedding, different graph embeddings contain diverse specific knowledge for generating the words with…
Segmenting unseen objects is a crucial ability for the robot since it may encounter new environments during the operation. Recently, a popular solution is leveraging RGB-D features of large-scale synthetic data and directly applying the model to unseen real-world scenarios. However, the domain shift…
Maneuvering an autonomous vehicle under drift condition is critical to the safety of autonomous vehicles when there is a sudden loss of traction due to external conditions such as rain or snow, which is a challenging control problem due to the presence of significant sideslip and nearly full saturat…
Image hashing is to represent an image using a binary code for efficient storage and accurate retrieval. Recently, deep hashing methods have shown great improvements on ideally balanced datasets, however, long-tailed data is more common due to rare samples or data collection costs in the real world.…
Current metrics for video captioning are mostly based on the text-level comparison between reference and candidate captions. However, they have some insuperable drawbacks, e.g., they cannot handle videos without references, and they may result in biased evaluation due to the one-to-many nature of vi…
Deep learning-based methods have shown excellent potential on object detection and pose estimation with vast amounts of training data to achieve good performance. Obtaining enough comprehensive manual labeling training data is a time-consuming and error-prone task in industrial scenes, and most curr
Deep learning models have shown to be susceptible to universal adversarial perturbation (UAP), which has aroused wide concerns in the community. Compared with the conventional adversarial attacks that generate adversarial samples at the instance level, UAP can fool the target model for different ins…
Online class-incremental continual learning aims to learn new classes continually from a never-ending and single-pass data stream, while not forgetting the learned knowledge of old classes. Existing replay-based methods have shown promising performance by storing a subset of old class data. Unfortun…
The transformer-based encoder-decoder framework has shown remarkable performance in image captioning. However, most transformer-based captioning methods ever overlook two kinds of elusive confounders: the visual confounder and the linguistic confounder, which generally lead to harmful bias, induce t…
We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an image codec, we aim to redesign the Vision Transformer (ViT) m…
We propose an Auto-Parsing Network (APN) to discover and exploit the input data's hidden tree structures for improving the effectiveness of the Transformer-based vision-language systems. Specifically, we impose a Probabilistic Graphical Model (PGM) parameterized by the attention operations on each s…
We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect causes harmful bias that misleads the attention module to focus on the spurious correlations in training data, damaging the m…
By contrasting positive-negative counterparts, graph contrastive learning has become a prominent technique for unsupervised graph representation learning. However, existing methods fail to consider the class information and will introduce false-negative samples in the random negative sampling, causi…
Modern deep learning methods have achieved great success in machine learning and computer vision fields by learning a set of pre-defined datasets. Howerver, these methods perform unsatisfactorily when applied into real-world situations. The reason of this phenomenon is that learning new tasks leads…
Deep clustering gradually becomes an important branch in unsupervised learning methods. However, current approaches hardly take into consideration the semantic sample relationships that existed in both local and global features. In addition, since the deep features are updated on-the-fly, relying on…
Graph convolution networks (GCNs) are a powerful deep learning approach and have been successfully applied to representation learning on graphs in a variety of real-world applications. Despite their success, two fundamental weaknesses of GCNs limit their ability to represent graph-structured data: p…
Deep clustering integrates embedding and clustering together to obtain the optimal nonlinear embedding space, which is more effective in real-world scenarios compared with conventional clustering methods. However, the robustness of the clustering network is prone to being attenuated especially when…
Change Captioning is a task that aims to describe the difference between images with natural language. Most existing methods treat this problem as a difference judgment without the existence of distractors such as viewpoint changes. However, in practice, viewpoint changes happen often and can overwh…
Despite the great progress in human motion prediction, it remains a challenging task due to the complicated structural dynamics of human behaviors. In this paper, we address this problem in three aspects. First, to capture the long-range spatial correlations and temporal dependencies, we apply a tra…
Zero-Shot Learning (ZSL) handles the problem that some testing classes never appear in training set. Existing ZSL methods are designed for learning from a fixed training set, which do not have the ability to capture and accumulate the knowledge of multiple training sets, causing them infeasible to m…
Classical subspace clustering methods often assume that the raw form data lie in a union of the low-dimension linear subspace. This assumption is too strict in practice, which largely limits the generalization of subspace clustering. To tackle this issue, deep subspace clustering (DSC) networks base…
We propose Scene Graph Auto-Encoder (SGAE) that incorporates the language inductive bias into the encoder-decoder image captioning framework for more human-like captions. Intuitively, we humans use the inductive bias to compose collocations and contextual inference in discourse. For example, when we…
The clustering methods have recently absorbed even-increasing attention in learning and vision. Deep clustering combines embedding and clustering together to obtain optimal embedding subspace for clustering, which can be more effective compared with conventional clustering methods. In this paper, we…
We do not speak word by word from scratch; our brain quickly structures a pattern like sth do sth at someplace and then fill in the detailed description. To render existing encoder-decoder image captioners such human-like reasoning, we propose a novel framework: learning to Collocate Neural Modules…
Most of current image captioning models heavily rely on paired image-caption datasets. However, getting large scale image-caption paired data is labor-intensive and time-consuming. In this paper, we present a scene graph-based approach for unpaired image captioning. Our framework comprises an image…
Multispectral pedestrian detection has shown great advantages under poor illumination conditions, since the thermal modality provides complementary information for the color image. However, real multispectral data suffers from the position shift problem, i.e. the color-thermal image pairs are not st…
Due to fact that it is prohibitively expensive to completely annotate visual relationships, ie, the (obj1, rel, obj2) triplets, relationship models are inevitably biased to object classes of limited pairwise patterns, leading to poor generalization to rare or unseen object combinations. Therefore, w…