5 papers
Embedding Rotation Invariance for Provable Multi-Oriented Scene Text Recognition
Zhibin Ma, Pengwen Dai, Yi Liu +3
Multi-oriented text is ubiquitous in real-world scenes and remains a major challenge for scene text recognition (STR). Existing rotation-aware methods explicitly estimate text orie…
Beyond Symmetric Fusion: Exploiting Task-Dependent Modality Strengths for RGB-Event Small Object Detection
Ziheng Wang, Chaolang Li, Yutong Yang +5
State-of-the-art RGB-Event detectors improve the detection of small, fast-moving objects by combining complementary features from RGB and Event data, yet they typically fuse the tw…
EagleNet: Energy-Aware Fine-Grained Relationship Learning Network for Text-Video Retrieval
Yuhan Chen, Pengwen Dai, Chuan Wang +2
Text-video retrieval tasks have seen significant improvements due to the recent development of large-scale vision-language pre-trained models. Traditional methods primarily focus o…
Decoupled Graph Energy-based Model for Node Out-of-Distribution Detection on Heterophilic Graphs
Yuhan Chen, Yihong Luo, Yifan Song +3
Despite extensive research efforts focused on OOD detection on images, OOD detection on nodes in graph learning remains underexplored. The dependence among graph nodes hinders the…
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats
Kuanrong Liu, Siyuan Liang, Jiawei Liang +2
Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to back…