13 papers
Trimodal Context-Aware Micro-Expression Recognition in Real-World Conversations: A Dataset and a Hierarchical Fusion Network
Junbo Wang, Yan Zhao, Shigang Wang +3
Recognizing micro-expressions in real-world conversations is challenging, as these facial movements are brief and faint, and their interpretations are strongly dependent on the con…
Tree-of-Experience: Hierarchical Experience Management for Self-Evolving Agents
Zihao Deng, Yining Zhu, Leiming Wang +2
Continual self-evolution requires LLM agents to transform environmental interactions into reliable and reusable experience. Existing methods typically refine individual trajectorie…
Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning
Liangyu Fu, Junbo Wang, Yuke Li +3
Text-only training is a popular paradigm in zero-shot video captioning, where the video distribution is not available to the model during training, leading to a cross-modal gap bet…
TDVR: Joint Text Disambiguation and Viewpoint Reasoning for Zero-Shot 3D Visual Grounding
Qingxi Du, Junbo Wang, Yuke Li +1
Zero-shot 3D visual grounding aims to localize specific objects based on textual descriptions and 3D visual input. However, the effectiveness of existing methods is significantly h…
Adaptive Emotional Video Captioning via Affective Heterogeneous Graph Reasoning and Multi-task Joint Learning
Junbo Wang, Liangyu Fu, Yuke Li +2
Emotional video captioning (EVC) aims to describe a video with both factual correctness and affective expressiveness. It requires a model to perceive subtle, ambiguous, and tempora…
FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewards
Zihao Deng, Yining Zhu, Leiming Wang +7
Large language model (LLM) agents increasingly rely on external experience to continually adapt to changing environments without modifying their underlying models. Recent experienc…
EPIR: An Efficient Patch Tokenization, Integration and Representation Framework for Micro-expression Recognition
Junbo Wang, Liangyu Fu, Yuke Li +3
Micro-expression recognition can obtain the real emotion of the individual at the current moment. Although deep learning-based methods, especially Transformer-based methods, have a…
DiffVC: A Non-autoregressive Framework Based on Diffusion Model for Video Captioning
Junbo Wang, Liangyu Fu, Yuke Li +4
Current video captioning methods usually use an encoder-decoder structure to generate text autoregressively. However, autoregressive methods have inherent limitations such as slow…
SAMAS: A Spectrum-Guided Multi-Agent System for Achieving Style Fidelity in Literary Translation
Jingzhuo Wu, Jiajun Zhang, Keyan Jin +2
Modern large language models (LLMs) excel at generating fluent and faithful translations. However, they struggle to preserve an author's unique literary style, often producing sema…
ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment
Wanjiang Weng, Xiaofeng Tan, Junbo Wang +3
Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based me…
MMED: A Multimodal Micro-Expression Dataset based on Audio-Visual Fusion
Junbo Wang, Yan Zhao, Shuo Li +3
Micro-expressions (MEs) are crucial leakages of concealed emotion, yet their study has been constrained by a reliance on silent, visual-only data. To solve this issue, we introduce…
Foundation Model for Skeleton-Based Human Action Understanding
Hongsong Wang, Wanjiang Weng, Junbo Wang +4
Human action understanding serves as a foundational pillar in the field of intelligent motion perception. Skeletons serve as a modality- and device-agnostic representation for huma…
USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation
Wanjiang Weng, Hongsong Wang, Junbo Wang +2
Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating…