94 citations · 152 across the 18 of their papers we have counts for
19 papers
Fysiverse-3D-Vision Technical Report: Generating Executable 3D Worlds from Images through Unified Spatial Reasoning
Dingkang Yang, Yizhou Liu, Wendong Cheng +5
Generative models have advanced image-conditioned 3D content creation, yet generating controllable and executable 3D scenes from a single image remains challenging. Existing 3D gen…
OmniFysics-Nano-V2 Technical Report: Understanding the Physical World Across Modalities
Yizhou Liu, Jinghang Han, Kaixiang Qiu +8
Omni-modal models have expanded multimodal interaction across vision, audio, speech, and language. However, their training is predominantly organized around semantic descriptions a…
OmniFysics-Captioner Technical Report: Grounding Omni-Modal Understanding in the Physical World for Better Captioning
Kaixiang Qiu, Minghao Han, Keliang Liu +7
Building omni-modal models with physical intelligence requires fine-grained supervision that captures physical evidence such as contact, support, deformation, and state transitions…
Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning
Mingcheng Li, Dingkang Yang, Yang Liu +11
Multimodal Sentiment Analysis (MSA) is an important research area that aims to understand and recognize human sentiment through multiple modalities. The complementary information p…
MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation
Xiao Zhao, Xukun Zhang, Dingkang Yang +4
Accurate and robust multimodal multi-task perception is crucial for modern autonomous driving systems. However, current multimodal perception research follows independent paradigms…
Faster Diffusion Action Segmentation
Shuaibing Wang, Shunli Wang, Mingcheng Li +4
Temporal Action Segmentation (TAS) is an essential task in video analysis, aiming to segment and classify continuous frames into distinct action segments. However, the ambiguous bo…
CoMT: Chain-of-Medical-Thought Reduces Hallucination in Medical Report Generation
Yue Jiang, Jiawei Chen, Dingkang Yang +5
Automatic medical report generation (MRG), which possesses significant research value as it can aid radiologists in clinical diagnosis and report composition, has garnered increasi…
Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
Jiawei Chen, Dingkang Yang, Tong Wu +7
Large Vision Language Models (LVLMs) are increasingly integral to healthcare applications, including medical visual question answering and imaging report generation. While these mo…
PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
Dingkang Yang, Jinjie Wei, Dongling Xiao +11
Developing intelligent pediatric consultation systems offers promising prospects for improving diagnostic efficiency, especially in China, where healthcare resources are scarce. De…
Robust Emotion Recognition in Context Debiasing
Dingkang Yang, Kun Yang, Mingcheng Li +3
Context-aware emotion recognition (CAER) has recently boosted the practical applications of affective computing techniques in unconstrained environments. Mainstream CAER methods in…
HandGCAT: Occlusion-Robust 3D Hand Mesh Reconstruction from Monocular Images
Shuaibing Wang, Shunli Wang, Dingkang Yang +4
We propose a robust and accurate method for reconstructing 3D hand mesh from monocular images. This is a very challenging problem, as hands are often severely occluded by objects.…
CPR-Coach: Recognizing Composite Error Actions based on Single-class Training
Shunli Wang, Qing Yu, Shuaibing Wang +7
The fine-grained medical action analysis task has received considerable attention from pattern recognition communities recently, but it faces the problems of data and algorithm sho…
AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception
Dingkang Yang, Shuai Huang, Zhi Xu +12
Driver distraction has become a significant cause of severe traffic accidents over the past decade. Despite the growing development of vision-driven driver monitoring systems, the…
Text-oriented Modality Reinforcement Network for Multimodal Sentiment Analysis from Unaligned Multimodal Sequences
Yuxuan Lei, Dingkang Yang, Mingcheng Li +3
Multimodal Sentiment Analysis (MSA) aims to mine sentiment information from text, visual, and acoustic modalities. Previous works have focused on representation learning and featur…
Context De-confounded Emotion Recognition
Dingkang Yang, Zhaoyu Chen, Yuzheng Wang +8
Context-Aware Emotion Recognition (CAER) is a crucial and challenging task that aims to perceive the emotional states of the target person with contextual information. Recent appro…
Towards Simultaneous Segmentation of Liver Tumors and Intrahepatic Vessels via Cross-attention Mechanism
Haopeng Kuang, Dingkang Yang, Shunli Wang +2
Accurate visualization of liver tumors and their surrounding blood vessels is essential for noninvasive diagnosis and prognosis prediction of tumors. In medical image segmentation,…
CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in Space
Shunli Wang, Shuaibing Wang, Bo Jiao +5
Reliable and stable 6D pose estimation of uncooperative space objects plays an essential role in on-orbit servicing and debris removal missions. Considering that the pose estimator…
A Survey of Video-based Action Quality Assessment
Shunli Wang, Dingkang Yang, Peng Zhai +5
Human action recognition and analysis have great demand and important application significance in video surveillance, video retrieval, and human-computer interaction. The task of h…
TSA-Net: Tube Self-Attention Network for Action Quality Assessment
Shunli Wang, Dingkang Yang, Peng Zhai +2
In recent years, assessing action quality from videos has attracted growing attention in computer vision community and human computer interaction. Most existing approaches usually…