139 accepted papers
Few-shot Semantic Segmentation (FSS) aims to segment objects of novel categories given only a handful of labeled examples. However, existing methods often rely on complex category-specific modeling, resulting in high computational cost and limited generalization under low-data regimes. To address th
Multimodal Large Language Models are primarily trained and evaluated on aligned image-text pairs, which leaves their ability to detect and resolve real-world inconsistencies largely unexplored. In open-domain applications visual and textual cues often conflict, requiring models to perform structured
Test-time scaling methods such as majority vote aggregation and iterative refinement (e.g., self-reflection or multi-agent inference) improve reasoning performance by leveraging multiple solution samples. However, their efficacy depends not only on raw performance, but critically on the distribution…
Object-Goal Navigation (ObjectNav) requires an embodied agent to search for and reach a target object category in previously unseen environments using only onboard egocentric observations, which is a fundamental capability for long-horizon autonomous robots. Current Object-Goal Navigation methods ty…
Out-of-Town (OOT) recommendation aims to provide personalized suggestions for users in unfamiliar cities. However, OOT recommendation faces two fundamental challenges: the difficulty of reasoning across modalities, as preference signals in disparate formats such as images and text are hard to compar
Following the success of Group Relative Policy Optimization (GRPO) in foundation LLMs, an increasing number of works have sought to adapt GRPO to Visual Large Language Models (VLLMs) for visual perception tasks (e.g., detection and segmentation). However, much of this line of research rests on a lon
Test-Time Adaptation (TTA) is essential for enabling deep learning models to handle real-world data distribution shifts. However, current approaches face significant limitations: backpropagation-based methods are not suitable for low-end deployment devices, due to their high computation and memory r
3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering. Nevertheless, its practicality is constrained by the high memory cost due to a huge number of Gaussian points. Many pruning-based 3DGS variants have been proposed for memory saving
Automated scoring of written constructed responses typically relies on separate models per task, straining computational resources, storage, and maintenance in real-world education settings. We propose UniMoE-Guided, a knowledge-distilled multi-task Mixture-of-Experts (MoE) approach that transfers e
Distributional learning problems optimize discrepancies between probability measures, including optimal transport or Sinkhorn divergence, yet are typically optimized using Euclidean first-order methods in parameter space. We show this mismatch is structural rather than algorithmic. We introduce geom…
Multimodal Knowledge Editing (MKE) extends traditional knowledge editing to settings involving both textual and visual modalities. However, existing MKE benchmarks primarily assess final answer correctness, neglecting the quality of intermediate reasoning and robustness to visually rephrased inputs.
Regional refinement for interactive segmentation is of great necessity to ensure the fidelity of segmented pixels nearby user-prompted locations, which specifies a local window (\ie, focus view) for the latest click after a global prediction, where local pixels are revisited and optimized using nume…
Clinical Computed Tomography (CT) reconstruction often faces mixed degradations, where quantum noise, streak artifacts, and geometric distortions co-occur with various compositions and severities. Recently, all-in-one frameworks have outperformed traditional single-task models through degradation-sp
Object-level SLAM offers structured and semantically meaningful environment representations, making it more interpretable and suitable for high-level robotic tasks. However, most existing approaches rely on RGB-D sensors or monocular views, which suffer from narrow fields of view, occlusion sensitiv
We introduce MedAgentGym, a scalable and interactive training environment designed to enhance coding-based biomedical reasoning capabilities in large language model (LLM) agents. MedAgentGym comprises 72,413 task instances across 129 categories derived from 12 authentic real-world biomedical scenari…
Recent advances in 3D Gaussian Splatting (3DGS) have enabled highly efficient and photorealistic novel view synthesis. However, segmenting objects accurately in 3DGS remains challenging due to the discrete nature of Gaussian representations, which often leads to aliasing and artifacts at object boun
Prediction sets can wrap around any ML model to cover unknown test outcomes with a guaranteed probability. Yet, it remains unclear how to use them optimally for downstream decision-making. Here, we propose a decision-theoretic framework that seeks to minimize the expected loss (risk) against a worst…
On-policy deep reinforcement learning remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy and policy updates must be conservative. In this paper, w…
Conformal prediction can be used to construct prediction sets that cover the true outcome with a desired probability, but can sometimes lead to large prediction sets that are costly in practice. The most useful outcome is a singleton prediction---an unambiguous decision---yet existing efficiency-ori…
While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, particularly under uncertainty, given ill-posed or ambiguous queries. We introduce statistically principled early stopping methods that monitor uncertainty s…
Text-to-Audio-Video (T2AV) generation aims to synthesize temporally coherent video and semantically synchronized audio from natural language, yet its evaluation remains fragmented, often relying on unimodal metrics or narrowly scoped benchmarks that fail to capture cross-modal alignment, instruction…
Soft grippers conform to the shape and surface properties of the objects to be grasped, effectively avoiding damage to soft and fragile items. Despite the variety of existing soft gripper designs, their structures lack sufficient flexibility for effectively grasping slender objects or operating in n
Recent graph-based multi-view clustering (GMVC) methods typically encode view features into high-dimensional spaces and construct graphs based on distance similarity. However, the high dimensionality of the embeddings often leads to the hubness problem, where a few points repeatedly appear in the ne…
While humans effortlessly draw visual objects and shapes by adaptively allocating attention based on their complexity, existing multimodal large language models (MLLMs) remain constrained by rigid token representations. Bridging this gap, we propose ALTo, an adaptive length tokenizer for autoregress…
Fraudulent activities have caused substantial negative social impacts and are exhibiting emerging characteristics such as intelligence and industrialization, posing challenges of high-order interactions, intricate dependencies, and the sparse yet concealed nature of fraudulent entities. Existing gra…
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
In recent years, speech diffusion models have advanced rapidly. Alongside the widely used U-Net architecture, transformer-based models such as the Diffusion Transformer (DiT) have also gained attention. However, current DiT speech models treat Mel spectrograms as general images, which overlooks the…
For quadrupeds, a flexible spine allows them to traverse space and make quick turns. From the perspective of mechanical design in quadruped robots, an active spine with 2 degrees of freedom (2-DOF) can achieve dynamic posture adjustment similar to biological organisms which allows for pitch and yaw
Top-$k$ decoding is a widely used method for sampling from LLMs: at each token, only the largest $k$ next-token-probabilities are kept, and the next token is sampled after re-normalizing them to sum to unity. Top-$k$ and other sampling methods are motivated by the intuition that true next-token dist…
Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. While existing methods attempt to achieve this through either direct instruction-response synthesis or preferential response optimization, they often str…
3D Gaussian Splatting (3DGS) has emerged as a powerful technique for radiance field rendering, but it typically requires millions of redundant Gaussian primitives, overwhelming memory and rendering budgets. Existing compaction approaches address this by pruning Gaussians based on heuristic importanc…
Heterogeneous robots can work together to accomplish a variety of complex tasks and have shown great potential in many fields. There are many efforts to make robot task orchestration more efficient. However, current methods still have some limitations, including the lack of a high-level abstraction
The remarkable performance of large multimodal models (LMMs) has attracted significant interest from the image segmentation community.To align with the next-token-prediction paradigm, current LMM-driven segmentation methods either use object boundary points to represent masks or introduce special se…
3D Multi-Object Tracking (MOT) provides the trajectories of surrounding objects, assisting robots or vehicles in smarter path planning and obstacle avoidance. Existing 3D MOT methods based on the Tracking-by-Detection framework typically use a single motion model to track an object throughout its en
Modern policy gradient algorithms, such as TRPO and PPO, outperform vanilla policy gradient in many RL tasks. Questioning the common belief that enforcing approximate trust regions leads to steady policy improvement in practice, we show that the more critical factor is the enhanced value estimation…
Low-light image enhancement problem has been widely studied. However, most existing methods do not perform well on low-light face images due to no specific facial characteristic considerations. We first create large-scale low-light face datasets with synthesized and real-world images to address the…
Explainable fake news detection predicts the authenticity of news items with annotated explanations. Today, Large Language Models (LLMs) are known for their powerful natural language understanding and explanation generation abilities. However, using LLMs for explainable fake news detection remains t…
Adverse weather conditions, such as rain, snow, and haze, introduce complex degradations that present substantial challenges for effective image restoration. Existing all-in-one models often rely on fixed network structures, limiting their ability to adapt to the varying characteristics of different…
We present a robust underwater navigation system that integrates magnetic, visual, and inertial measurements from commercial off-the-shelf sensors. Visual Inertial Navigation Systems (VINS) face challenges when used for Autonomous Underwater Vehicle (AUV) localization in perceptually degraded enviro
Physically-based rendering (PBR) has become a cornerstone in modern computer graphics, enabling realistic material representation and lighting interactions in 3D scenes. In this paper, we present MaterialMVP, a novel end-to-end model for generating PBR textures from 3D meshes and image prompts, addr…
Open-Ended object Detection (OED) is a novel and challenging task that detects objects and generates their category names in a free-form manner, without requiring additional vocabularies during inference. However, the existing OED models, such as GenerateU, require large-scale datasets for training,…
The deployment of large language models (LLMs) faces considerable challenges concerning resource constraints and inference efficiency. Recent research has increasingly focused on smaller, task-specific models enhanced by distilling knowledge from LLMs. However, prior studies have often overlooked th
Large Language Models (LLMs) capable of handling extended contexts are in high demand, yet their inference remains challenging due to substantial Key-Value (KV) cache size and high memory bandwidth requirements. Previous research has demonstrated that KV cache exhibits low-rank characteristics withi…
Legged aerial-terrestrial robots have garnered significant research attention in recent years due to their enhanced environmental adaptability through combined aerial and terrestrial locomotion. However, existing passive spring-legged aerial robots exhibit limited motion versatility, demonstrating s
Under-display Camera is an emerging technology for full-screen display with a camera under the display. However, the current implementation of UDC causes serious image degradation. Incident light required for camera imaging undergoes attenuation and diffraction when passing through the display. Curr…
Text-to-motion generation, which translates textual descriptions into human motions, has been challenging in accurately capturing detailed user-imagined motions from simple text inputs. This paper introduces StickMotion, an efficient diffusion-based network designed for multi-condition scenarios, wh…
Significant advancements has recently been achieved in the field of multi-modal large language models (MLLMs), demonstrating their remarkable capabilities in understanding and reasoning across diverse tasks. However, these models are often trained for specific tasks and rely on task-specific input-o…
Recent advances in speech spoofing necessitate stronger verification mechanisms in neural speech codecs to ensure authenticity. Current methods embed numerical watermarks before compression and extract them from reconstructed speech for verification, but face limitations such as separate training pr…
In indoor environments where the Global Navigation Satellite System (GNSS) isn’t available, the infrastructure-based LiDAR-camera joint array can provide high-precision localization for mobile robots, such as Autonomous Valet Parking (AVP). The primary challenge in employing the infrastructure-based…
KL-regularized reinforcement learning (RL) is a popular alignment framework to control the language model responses towards high reward outcomes. We pose a tokenwise RL objective and propose a modular solver for it, called *controlled decoding (CD)*. CD exerts control through a separate *prefix scor…
Reprogrammable design enables soft actuators to change their performances after fabrication and obtain new deformation modes and functions. The reprogrammable design of soft pneumatic actuators is relatively difficult due to the intrinsic material being chemically inactive. This work proposes a new
Graph neural networks (GNNs) are recognized for their strong performance across various applications, with the backpropagation (BP) algorithm playing a central role in the development of most GNN models. However, despite its effectiveness, BP has limitations that challenge its biological plausibilit…
Negative-pressure artificial muscles based on internal support and flexible skin provide a way to develop high-performance artificial muscles. However, the random and disordered skin wrinkles formed during the contraction may lead to uncertainty in the actuation behavior, and the flexible but inexte
Language model based text-to-speech (TTS) models, like VALL-E, have gained attention for their outstanding in-context learning capability in zero-shot scenarios. Neural speech codec is a critical component of these models, which can convert speech into discrete token representations. However, excess…
Few-shot 3D point cloud semantic segmentation aims to segment query point clouds with only a few annotated support point clouds. Existing prototype-based methods learn prototypes from the 3D support set to guide the segmentation of query point clouds. However, they encounter the challenge of low pro…
Multi-modal large language models (MLLMs) have demonstrated remarkable performance across various tasks. However, these models often prioritize capturing global information and overlook the importance of perceiving local information. This limitation hinders their ability to effectively understand fi…
For fine-grained generation and recognition tasks such as minimally-supervised text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), the intermediate representations extracted from speech should serve as a "bridge" between text and acoustic information, containing info…
Recently, there has been a growing interest in text-to-speech (TTS) methods that can be trained with minimal supervision by combining two types of discrete speech representations and using two sequence-to-sequence tasks to decouple TTS. However, existing methods suffer from three problems: the high-…
Policy gradient methods have enabled deep reinforcement learning (RL) to approach challenging continuous control problems, even when the underlying systems involve highly nonlinear dynamics that generate complex non-smooth optimization landscapes. We develop a rigorous framework for understanding ho…
"Personalization is an important topic in text-to-image generation, especially the challenging multi-concept personalization. Current multi-concept methods are struggling with identity preservation, occlusion, and the harmony between foreground and background. In this work, we propose OMG, an occlus…
We present PANORAMIA, a privacy leakage measurement framework for machine learning models that relies on membership inference attacks using generated data as non-members. By relying on generated non-member data, PANORAMIA eliminates the common dependency of privacy measurement tools on in-distributi…
Federated learning achieves effective performance in modeling decentralized data. In practice client data are not well-labeled which makes it potential for federated unsupervised learning (FUSL) with non-IID data. However the performance of existing FUSL methods suffers from insufficient representat…
Predicting human pose sequences via existing pose estimators often encounters various estimation errors. Motion refinement methods aim to optimize the predicted human pose sequences from pose estimators while ensuring minimal computational overhead and latency. Prior investigations have primarily co…
With the increasing need for facial behavior analysis, semi-supervised AU intensity estimation using only keyframe annotations has emerged as a practical and effective solution to relieve the burden of annotation. However, the lack of annotations makes the spurious correlation problem caused by AU c…
Key-value (KV) caching is an important technique to accelerate the inference of large language models (LLMs), but incurs significant memory overhead. To compress the size of KV cache, existing methods often compromise precision or require extra data for calibration, limiting their practicality in LL…
By incorporating the latest external knowledge, large language models (LLMs) can modify their internal memory. However, in practical applications, LLMs may encounter outdated information, necessitating the filtering of such data and updating of knowledge beyond internal memory. This paper explores w…
Correspondence pruning aims to find correct matches (inliers) from an initial set of putative correspondences, which is a fundamental task for many applications. The process of finding is challenging, given the varying inlier ratios between scenes/image pairs due to significant visual differences. H…
In recent years, Visual-Inertial Odometry (VIO) has demonstrated remarkable results using low-cost and complementary sensors. However, these methods often encounter initialization failure and suffer reduced robustness or low trajectory accuracy under challenging scenarios. In this letter, we propose
Existing object detection models are mainly trained on large-scale labeled datasets. However, annotating data for novel aerial object classes is expensive since it is time-consuming and may require expert knowledge. Thus, it is desirable to study label-efficient object detection methods on aerial im…
Automatic metrics play a crucial role in machine translation. Despite the widespread use of n-gram-based metrics, there has been a recent surge in the development of pre-trained model-based metrics that focus on measuring sentence semantics. However, these neural metrics, while achieving higher corr…
Very high-resolution (VHR) aerial image scene classification is an essential task for aerial image understanding. Although transformer-based models have demonstrated strong ability in natural image classification, transformer-based methods on VHR aerial image tasks are still lack of concern because…
Policy gradient lies at the core of deep reinforcement learning (RL) in continuous domains. Despite much success, it is often observed in practice that RL training with policy gradient can fail for many reasons, even on standard control problems with known solutions. We propose a framework for under…
This paper presents a novel transformer architecture for graph representation learning. The core insight of our method is to fully consider the information propagation among nodes and edges in a graph when building the attention module in the transformer blocks. Specifically, we propose a new attent…
In speech translation, leveraging multimodal data to improve model performance and address limitations of individual modalities has shown significant effectiveness. In this paper, we harness the complementary strengths of speech and text to improve speech translation. However, speech and text are di…
Open vocabulary object detection has been greately advanced by the recent development of vision-language pre-trained model, which helps recognizing the novel objects with only semantic categories. The prior works mainly focus on knowledge transferring to the object proposal classification and employ…
Widely-used DNN models are vulnerable to backdoor attacks, where the backdoored model is only triggered by specific inputs but can maintain a high prediction accuracy on benign samples. Existing backdoor input detection strategies rely on the assumption that benign and poisoned samples are separable…
The adversarial attacks have attracted increasing attention in various fields including natural language processing. The current textual attacking models primarily focus on fooling models by adding character-/word-/sentence-level perturbations, ignoring their influence on human perception. In this p…
Metal artifacts degrade CT image’s quality. Recently, some deep learning-based metal artifact reduction (MAR) methods have been developed. Supervised MAR methods don’t perform well in clinical due to the domain gap between simulated and clinical data. Although this problem can be avoided in an unsup…
As the quality of optical sensors improves, there is a need for processing large-scale images. In particular, the ability of devices to capture ultra-high definition (UHD) images and video places new demands on the image processing pipeline. In this paper, we consider the task of low-light image enh…
Medical code prediction from clinical notes aims at automatically associating medical codes with the clinical notes. Rare code problem, the medical codes with low occurrences, is prominent in medical code prediction. Recent studies employ deep neural networks and the external knowledge to tackle it.…
The current design based on air chambers makes thin wall a typical feature of soft robotic arms. Considering this characteristic, a new static modeling method that integrates the principle of virtual work and a spring-fluid equivalent modeling idea is proposed in this work. The method is able to con
Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021. However, the recent shared tasks have not covered many real-life and challenging scenarios. The first Audio Deep synthesis Detection challenge (ADD) was motivated to fill in the gap. The ADD 2022 includes three t…
"Palmprints are private and stable information for biometric recognition. In the deep learning era, the development of palmprint recognition is limited by the lack of sufficient training data. In this paper, by observing that palmar creases are the key information to deep-learning-based palmprint re…
Subject-invariant facial action unit (AU) recognition remains challenging for the reason that the data distribution varies among subjects. In this paper, we propose a causal inference framework for subject-invariant facial action unit recognition. To illustrate the causal effect existing in AU recog…
The text-based speech editor allows the editing of speech through intuitive cutting, copying, and pasting operations to speed up the process of editing speech. However, the major drawback of current systems is that edited speech often sounds unnatural and it is not obvious how to synthesize records…
In recent years, self-supervised representation learning for skeleton-based action recognition has been developed with the advance of contrastive learning methods. The existing contrastive learning methods use normal augmentations to construct similar positive samples, which limits the ability to ex…
In this article, a multi-DOF manipulator driven by novel hysteresis-attenuated pneumatic artificial muscles (PAMs) is designed, and the multi-DOF manipulator is composed of three manipulator units assembled in cascade, and each manipulator is driven by hysteresis-attenuated PAMs. Compared with the c
We address the efficiency problem of personalized ranking from implicit feedback by hashing users and items with binary codes, so that top-N recommendation can be fast executed in a Hamming space by bit operations. However, current hashing methods for top-N recommendation fail to align their learnin…
Federated learning (FL) is a privacy-preserving distributed machine learning paradigm that enables multiple clients to collaboratively train statistical models without disclosing raw training data. However, the inaccessible local training data and uninspectable local training process make FL suscept…
Scaling language models with more data, compute and parameters has driven significant progress in natural language processing. For example, thanks to scaling, GPT-3 was able to achieve strong results on in-context learning tasks. However, training these large dense models requires significant amount…
The semantic segmentation of LiDAR in the outdoor environment is still an open problem in the field of automatic driving. Although the emerging development and technological advancements, it remains challenging for three reasons: 1) uneven distribution of LiDAR Points in 3D space; 2) the same object
Recently, Multi-modal Named Entity Recognition (MNER) has attracted a lot of attention. Most of the work utilizes image information through region-level visual representations obtained from a pretrained object detector and relies on an attention mechanism to model the interactions between image and…
"Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. It remains challenging to identify small or sparse face image clusters that we call hard clusters, which is caused by the heterogeneity, i.e., high variations in size and sparsity, of th…
Defect detection has been widely studied in computer vision and used in industrial production. However, most existing methods for defect detection mainly suffer three drawbacks: i) Low-contrast problem between defects and background. ii) Large scale changes in defects size. iii) Extreme imbalance pr…
Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching, but these graph-based method…
Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses. In this paper, we propose a novel self-supervised approach that allo…
Graph Convolutional Networks (GCNs) have been widely applied in various fields due to their significant power on processing graph-structured data. Typical GCN and its variants work under a homophily assumption (i.e., nodes with same class are prone to connect to each other), while ignoring the heter…
Although image restoration has achieved significant progress, its potential to assist object detectors in adverse imaging conditions lacks enough attention. It is reported that the existing image restoration methods cannot improve the object detector performance and sometimes even reduce the detecti…
"Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors…
Recently, contrastive learning has shown great potential in medical image segmentation. Due to the lack of expert annotations, however, it is challenging to apply contrastive learning in semi-supervised scenes. To solve this problem, we propose a novel uncertainty-guided pixel contrastive learning m…
Transition systems usually contain various dynamic structures (e.g., stacks, buffers). An ideal transition-based model should encode these structures completely and efficiently. Previous works relying on templates or neural network structures either only encode partial structure information or suffe…
Automatic translation of dialogue texts is a much needed demand in many real life scenarios. However, the currently existing neural machine translation delivers unsatisfying results. In this paper, we conduct a deep analysis of a dialogue corpus and summarize three major issues on dialogue translati…
Pretrained contextualized embeddings are powerful word representations for structured prediction tasks. Recent work found that better word representations can be obtained by concatenating different types of embeddings. However, the selection of embeddings to form the best concatenated representation…
End-to-end framework can generate high-quality and high-similarity speech in the personalized speech synthesis task. However, the generalization of out-of-domain texts is still a challenging task. Limited target data leads to unacceptable errors and poor prosody and similarity performance of the syn…
In this letter, we focus on designing an effective method for lightweight and accurate facial action unit (AU) detection, which is essential for emotional communication in most human-robot interaction scenarios. AU detection is a delicate and challenging task because the subtle fleeting appearance c
Legged locomotion in a complex environment requires careful planning of the footholds of legged robots. In this paper, a novel Deep Reinforcement Learning (DRL) method is proposed to implement multi-contact motion planning for hexapod robots moving on uneven plum-blossom piles. First, the motion of…
We present Multi-view Pose transformer (MvP) for estimating multi-person 3D poses from multi-view images. Instead of estimating 3D joint locations from costly volumetric representation or reconstructing the per-person 3D pose from multiple detected 2D poses as in previous methods, MvP directly regre…
Video instance segmentation is a challenging task that extends image instance segmentation to the video domain. Existing methods either rely only on single-frame information for the detection and segmentation subproblems or handle tracking as a separate post-processing step, which limit their capabi…
Recent advances in Named Entity Recognition (NER) show that document-level contexts can significantly improve model performance. In many application scenarios, however, such contexts are not available. In this paper, we propose to find external contexts of a sentence by retrieving and selecting a se…
Despite decades of efforts, robot navigation in a real scenario with volatility, uncertainty, complexity, and ambiguity (VUCA for short), remains a challenging topic. Inspired by the central nervous system (CNS), we propose a hierarchical multi-expert learning framework for autonomous navigation in…
Entity retrieval, which aims at disambiguating mentions to canonical entities from massive KBs, is essential for many tasks in natural language processing. Recent progress in entity retrieval shows that the dual-encoder structure is a powerful and efficient framework to nominate candidates if entiti…
Although recent research has witnessed a significant progress on the video deblurring task, these methods struggle to reconcile inference efficiency and visual quality simultaneously, especially on ultra-high-definition (UHD) videos (e.g., 4K resolution). To address the problem, we propose a novel d…
In structured prediction problems, cross-lingual transfer learning is an efficient way to train quality models for low-resource languages, and further improvement can be obtained by learning from multiple source languages. However, not all source models are created equal and some may hurt performanc…
Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant computation on some area like the background. In this work, we enc…
The paper describes the CASIA speech synthesis system entry for challenge M2VoC 2021. The low similarity and naturalness of synthesized speech remains a challenging problem for speaker adaptation with few resources. Since the end-to-end acoustic model is too complex to interpret, overfitting will oc…
Recently, deep learning-based image enhancement algorithms achieved state-of-the-art (SOTA) performance on several publicly available datasets. However, most existing methods fail to meet practical requirements either for visual perception or for computation efficiency, especially for high-resolutio…
Zero-shot sequence labeling aims to build a sequence labeler without human-annotated datasets. One straightforward approach is utilizing existing systems (source models) to generate pseudo-labeled datasets and train a target sequence labeler accordingly. However, due to the gap between the source an…
This paper presents Self-correcting Encoding (Secoco), a framework that effectively deals with noisy input for robust neural machine translation by introducing self-correcting predictors. Different from previous robust approaches, Secoco enables NMT to explicitly correct noisy inputs and delete spec…
Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation is typically the cross-entropy between the teacher and the student’s output distr…
Transformers, which are popular for language modeling, have been explored for solving vision tasks recently, e.g., the Vision Transformer (ViT) for image classification. The ViT model splits each image into a sequence of tokens with fixed length and then applies multiple Transformer layers to model…
During the last couple of years, convolutional neural networks (CNNs) have achieved significant success in the single image dehazing task. Unfortunately, most existing deep dehazing models have high computational complexity, which hinders their application to high-resolution images, especially for U…
Existing single image high dynamic range (HDR) reconstruction attempt to expand the range of luminance. They are not effective to generate plausible textures and colors in the reconstructed results, especially for high-density pixels in ultra-high-definition (UHD) images.To address these problems, w…
Adapting word order from one language to another is a key problem in cross-lingual structured prediction. Current sentence encoders (e.g., RNN, Transformer with position embeddings) are usually word order sensitive. Even with uniform word form representations (MUSE, mBERT), word order discrepancies…
Existing data-dependent hashing methods usually learn hash functions from pairwise or triplet data relationships, which only capture the data similarity locally, and often suffer from low learning efficiency and low collision rate. In this work, we propose a new global similarity metric, termed as c…
End-to-end speech synthesis can generate high-quality synthetic speech and achieve high similarity scores with low-resource adaptation data. However, the generalization of out-domain texts is still a challenging task. The limited adaptation data leads to unacceptable errors and the poor prosody perf…
Learning-based approaches to graph matching have been developed and explored for more than a decade, have grown rapidly in scope and popularity in recent years. However, previous learning-based algorithms, with or without deep learning strategy, mainly focus on the learning of node and/or edge affin…
Significant progress has been made with artistic robots. However, existing robots fail to produce high-quality portraits in a short time. In this work, we present a drawing robot, which can automatically transfer a facial picture to a vivid portrait, and then draw it on paper within two minutes aver…
Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution. We f…
Knowledge Distillation (KD) aims to distill the knowledge of a cumbersome teacher model into a lightweight student model. Its success is generally attributed to the privileged information on similarities among categories provided by the teacher model, and in this sense, only strong teacher models ar…
Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO. They tend to suffer performance drop on realistic datasets that are usually long-tailed. This work aims to study and a…
This paper addresses the problem of deformable surface tracking from monocular images. Specifically, we propose a graph-based approach that effectively explores the structure information of the surface to enhance tracking performance. Our approach solves simultaneously for feature correspondence, ou…
State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic cumbersome teacher model's output to get improved generalization.…
This paper introduces a new designed modular tactile sensing dexterous hand for domestic service robots. This fully-actuated hand consists of 1 palm and 3 fingers, with embedded tactile sensors, motors and control boards. The palm and each finger have 2 degrees of freedom (DOFs). The modular design…
To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe several significant challenges. First, the target domain data i…
This work presents a novel variable stiffness structure consisting of a fiber-constrained dielectric elastomer tube filled with insulating oil. The tensile stiffness of the structure can be adjusted by voltages and its initial value can be customized according to the initial pre-stretch of the mater…
This work presents a novel variable stiffness structure consisting of a fiber-constrained dielectric elastomer tube filled with insulating oil. The tensile stiffness of the structure can be adjusted by voltages and its initial value can be customized according to the initial pre-stretch of the mater
Tracking planar objects has a wide range of applications in robotics. Conventional template tracking algorithms, however, often fail to observe fast object motion or drift significantly after a period of time, due to drastic object appearance change. To address such challenges, we propose a novel co…
This paper presents an inchworm inspired soft robot composed of the soft body, the front foot as well as the back foot. Compared to the traditional inchworm-type robot consisting of rigid components, the driven mode for the soft robot is more simple. The soft robot inspired by the inchworm has highe…
Aiming at mimicking the jumping locomotion of water striders, a new continuous jumping robot on water is proposed. Compared with the horizontal rowing motion, the jumping capability of water striders is challengeable to imitate, since the impact force on water is easy to cause the sinking of the rob