collaborators

7 papers

cs.CV2025

ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding

Zhenxing Zhang, Yaxiong Wang, Lechao Cheng +3

We present ASAP, a new framework for detecting and grounding multi-modal media manipulation (DGM4).Upon thorough examination, we observe that accurate fine-grained cross-modal sema…

cs.CV2025

SSAM: Self-Supervised Association Modeling for Test-Time Adaption

Yaxiong Wang, Zhenqiang Zhang, Lechao Cheng +3

Test-time adaption (TTA) has witnessed important progress in recent years, the prevailing methods typically first encode the image and the text and design strategies to model the a…

cs.CV2025

Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach

Yan Zhang, Lechao Cheng, Yaxiong Wang +2

Micro-Action Recognition (MAR) aims to classify subtle human actions in video. However, annotating MAR datasets is particularly challenging due to the subtlety of actions. To this…

cs.CV2025

EntityCLIP: Entity-Centric Image-Text Matching via Multimodal Attentive Contrastive Learning

Yaxiong Wang, Yujiao Wu, Lianwei Wu +3

Recent advancements in image-text matching have been notable, yet prevailing models predominantly cater to broad queries and struggle with accommodating fine-grained query intentio…

cs.CV2025

Knowledge Swapping via Learning and Unlearning

Mingyu Xing, Lechao Cheng, Shengeng Tang +3

We introduce \textbf{Knowledge Swapping}, a novel task designed to selectively regulate knowledge of a pretrained model by enabling the forgetting of user\-specified information, r…

cs.CV2025

Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning

Fangwen Wu, Lechao Cheng, Shengeng Tang +4

Class-incremental learning (CIL) seeks to enable a model to sequentially learn new classes while retaining knowledge of previously learned ones. Balancing flexibility and stability…