activity
20242026
most citedVAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection

8 citations · 11 across the 13 of their papers we have counts for

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV2025

Disentangling Foreground and Background for vision-Language Navigation via Online Augmentation

Yunbo Xu, Xuesong Zhang, Jia Li +2

Following language instructions, vision-language navigation (VLN) agents are tasked with navigating unseen environments. While augmenting multifaceted visual representations has pr…

cs.CV2025

Generalizable Engagement Estimation in Conversation via Domain Prompting and Parallel Attention

Yangche Yu, Yin Chen, Jia Li +6

Accurate engagement estimation is essential for adaptive human-computer interaction systems, yet robust deployment is hindered by poor generalizability across diverse domains and c…

cs.CV2025

Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval

Jian Xiao, Zijie Song, Jialong Hu +4

Recent progress in text-video retrieval has been largely driven by contrastive learning. However, existing methods often overlook the effect of the modality gap, which causes ancho…

cs.CV2025

VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection

Hao Cheng, Zhiwei Zhao, Yichao He +4

Audiovisual emotion recognition (AVER) aims to infer human emotions from nonverbal visual-audio (VA) cues, offering modality-complementary and language-agnostic advantages. However…

cs.CV2025

Video Flow as Time Series: Discovering Temporal Consistency and Variability for VideoQA

Zijie Song, Zhenzhen Hu, Yixiao Ma +2

Video Question Answering (VideoQA) is a complex video-language task that demands a sophisticated understanding of both visual content and temporal dynamics. Traditional Transformer…

cs.CV2025

PhysioSync: Temporal and Cross-Modal Contrastive Learning Inspired by Physiological Synchronization for EEG-Based Emotion Recognition

Kai Cui, Jia Li, Yu Liu +3

Electroencephalography (EEG) signals provide a promising and involuntary reflection of brain activity related to emotional states, offering significant advantages over behavioral c…