99 citations · 756 across the 62 of their papers we have counts for
63 papers
Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation
Jia-Qi Lin, Yuangang Pan, Chang-Dong Wang +3
Test-Time Adaptation (TTA) methods aim to bridge the domain gap between the source and target domains. However, traditional TTA methods become ineffective when the label distributi…
Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering
Chi Zhang, Wei Yin, Gang Yu +5
In this study, we address the challenge of 3D scene structure recovery from monocular depth estimation. While traditional depth estimation methods leverage labeled datasets to dire…
Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection
Kairui Hu, Ming Yan, Joey Tianyi Zhou +3
Stance detection aims to identify the attitude expressed in a document towards a given target. Techniques such as Chain-of-Thought (CoT) prompting have advanced this task, enhancin…
Noisy-Correspondence Learning for Text-to-Image Person Re-identification
Yang Qin, Yingke Chen, Dezhong Peng +3
Text-to-image person re-identification (TIReID) is a compelling topic in the cross-modal community, which aims to retrieve the target person based on a textual query. Although nume…
Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification
Xinke Li, Junchi Lu, Henghui Ding +3
With the growth of 3D sensing technology, deep learning system for 3D point clouds has become increasingly important, especially in applications like autonomous vehicles where safe…
Provable Dynamic Fusion for Low-Quality Multimodal Data
Qingyang Zhang, Haitao Wu, Changqing Zhang +4
The inherent challenge of multimodal fusion is to precisely capture the cross-modal correlation and flexibly conduct cross-modal interaction. To fully release the value of each mod…
dugMatting: Decomposed-Uncertainty-Guided Matting
Jiawei Wu, Changqing Zhang, Zuoyong Li +3
Cutting out an object and estimating its opacity mask, known as image matting, is a key task in image and video editing. Due to the highly ill-posed issue, additional inputs, typic…
Calibrating Multimodal Learning
Huan Ma. Qingyang Zhang, Changqing Zhang, Bingzhe Wu +3
Multimodal machine learning has achieved remarkable progress in a wide range of scenarios. However, the reliability of multimodal learning remains largely unexplored. In this paper…
A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation from a Single RGB Image
Changlong Jiang, Yang Xiao, Cunlin Wu +4
3D interacting hand pose estimation from a single RGB image is a challenging task, due to serious self-occlusion and inter-occlusion towards hands, confusing similar appearance pat…
Dual Stage Stylization Modulation for Domain Generalized Semantic Segmentation
Gabriel Tjio, Ping Liu, Chee-Keong Kwoh +1
Obtaining sufficient labeled data for training deep models is often challenging in real-life applications. To address this issue, we propose a novel solution for single-source doma…
Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video
Wenzheng Zeng, Yang Xiao, Sicheng Wei +5
Real-time eyeblink detection in the wild can widely serve for fatigue detection, face anti-spoofing, emotion analysis, etc. The existing research efforts generally focus on single-…
Deep Negative Correlation Classification
Le Zhang, Qibin Hou, Yun Liu +4
Ensemble learning serves as a straightforward way to improve the performance of almost any machine learning algorithm. Existing deep ensemble methods usually naively train many dif…
Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation
Jiawei Du, Yidi Jiang, Vincent Y. F. Tan +2
Model-based deep learning has achieved astounding successes due in part to the availability of large-scale real-world data. However, processing such massive amounts of data comes a…
TFormer: 3D Tooth Segmentation in Mesh Scans with Geometry Guided Transformer
Huimin Xiong, Kunle Li, Kaiyuan Tan +4
Optical Intra-oral Scanners (IOS) are widely used in digital dentistry, providing 3-Dimensional (3D) and high-resolution geometrical information of dental crowns and the gingiva. A…
Meta Knowledge Condensation for Federated Learning
Ping Liu, Xin Yu, Joey Tianyi Zhou
Existing federated learning paradigms usually extensively exchange distributed models at a central solver to achieve a more powerful model. However, this would incur severe communi…
Sharpness-Aware Training for Free
Jiawei Du, Daquan Zhou, Jiashi Feng +2
Modern deep neural networks (DNNs) have achieved state-of-the-art performances but are typically over-parameterized. The over-parameterization may result in undesirably large gener…
Perceiving the World: Question-guided Reinforcement Learning for Text-based Games
Yunqiu Xu, Meng Fang, Ling Chen +3
Text-based games provide an interactive way to study natural language processing. While deep reinforcement learning has shown effectiveness in developing the game playing agent, th…
Trusted Multi-View Classification with Dynamic Evidential Fusion
Zongbo Han, Changqing Zhang, Huazhu Fu +1
Existing multi-view classification algorithms focus on promoting accuracy by exploiting different views, typically integrating them into common representations for follow-up tasks.…
Temporal Sentence Grounding in Videos: A Survey and Future Directions
Hao Zhang, Aixin Sun, Wei Jing +1
Temporal sentence grounding in videos (TSGV), \aka natural language video localization (NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that semantically…
Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation
Gabriel Tjio, Ping Liu, Joey Tianyi Zhou +1
Convolutional neural networks typically perform poorly when the test (target domain) and training (source domain) data have significantly different distributions. While this proble…
Parallel Attention Network with Sequence Matching for Video Grounding
Hao Zhang, Aixin Sun, Wei Jing +3
Given a video, video grounding aims to retrieve a temporal moment that semantically corresponds to a language query. In this work, we propose a Parallel Attention Network with Sequ…
Video Corpus Moment Retrieval with Contrastive Learning
Hao Zhang, Aixin Sun, Wei Jing +4
Given a collection of untrimmed and unsegmented videos, video corpus moment retrieval (VCMR) is to retrieve a temporal moment (i.e., a fraction of a video) that semantically corres…
Efficient Spiking Neural Networks with Radix Encoding
Zhehui Wang, Xiaozhe Gu, Rick Goh +2
Spiking neural networks (SNNs) have advantages in latency and energy efficiency over traditional artificial neural networks (ANNs) due to its event-driven computation mechanism and…
RCT: Resource Constrained Training for Edge AI
Tian Huang, Tao Luo, Ming Yan +2
Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devi…