3 citations · 13 across the 14 of their papers we have counts for
14 papers
Video = World + Event Stream
Lianghua Huang, Zhi-Fan Wu, Yupeng Shi +24
We present Wan-Streamer v0.3, which reframes our native-streaming interaction model under a single organizing view: a video is a world plus an event stream. The world is the persis…
Wan-Streamer v0.2: Higher Resolution, Same Latency
Lianghua Huang, Zhi-Fan Wu, Yupeng Shi +23
We present Wan-Streamer v0.2, a latency-preserving upgrade of the native-streaming, end-to-end audio-visual interaction model. v0.2 keeps the v0.1 modeling formulation, but raises…
GenAgent: Scaling Text-to-Image Generation via Agentic Multimodal Reasoning
Kaixun Jiang, Yuzheng Wang, Junjie Zhou +6
We introduce GenAgent, unifying visual understanding and generation through an agentic multimodal model. Unlike unified models that face expensive training costs and understanding-…
MMARD: Improving the Min-Max Optimization Process in Adversarial Robustness Distillation
Yuzheng Wang, Zhaoyu Chen, Dingkang Yang +2
Adversarial Robustness Distillation (ARD) is a promising task to boost the robustness of small-capacity models with the guidance of the pre-trained robust teacher. The ARD can be s…
Towards Context-Aware Emotion Recognition Debiasing from a Causal Demystification Perspective via De-confounded Training
Dingkang Yang, Kun Yang, Haopeng Kuang +3
Understanding emotions from diverse contexts has received widespread attention in computer vision communities. The core philosophy of Context-Aware Emotion Recognition (CAER) is to…
Self-Cooperation Knowledge Distillation for Novel Class Discovery
Yuzheng Wang, Zhaoyu Chen, Dingkang Yang +2
Novel Class Discovery (NCD) aims to discover unknown and novel classes in an unlabeled set by leveraging knowledge already learned about known classes. Existing works focus on inst…
De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts
Yuzheng Wang, Dingkang Yang, Zhaoyu Chen +5
Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data. Exist…
Debiased Multimodal Understanding for Human Language Sequences
Zhi Xu, Dingkang Yang, Mingcheng Li +5
Human multimodal language understanding (MLU) is an indispensable component of expression analysis (e.g., sentiment or humor) from heterogeneous modalities, including visual postur…
Towards Multimodal Sentiment Analysis Debiasing via Bias Purification
Dingkang Yang, Mingcheng Li, Dongling Xiao +7
Multimodal Sentiment Analysis (MSA) aims to understand human intentions by integrating emotion-related clues from diverse modalities, such as visual, language, and audio. Unfortuna…
Learning Causality-inspired Representation Consistency for Video Anomaly Detection
Yang Liu, Zhaoyang Xia, Mengyang Zhao +7
Video anomaly detection is an essential yet challenging task in the multimedia community, with promising applications in smart cities and secure communities. Existing methods attem…
Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation
Siao Liu, Zhaoyu Chen, Yang Liu +8
Learning a policy with great generalization to unseen environments remains challenging but critical in visual reinforcement learning. Despite the success of augmentation combinatio…
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…
Sampling to Distill: Knowledge Transfer from Open-World Data
Yuzheng Wang, Zhaoyu Chen, Jie Zhang +7
Data-Free Knowledge Distillation (DFKD) is a novel task that aims to train high-performance student models using only the pre-trained teacher network without original training data…
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…