9 papers
Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence
Jiahao Meng, Zhongyuan Bao, Yue Tan +7
Reliable video reasoning requires models to produce correct answers and expose supporting visual evidence. Open-o3-Video enables verifiable reasoning by embedding timestamps and ob…
MotionAtlas: Detailed Region Captioning for Motion-Centric Videos
Weisong Liu, Haochen Wang, Kuan Gao +8
We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to co…
Towards One-to-Many Temporal Grounding
Qi Xu, Yue Tan, Shihao Chen +5
Temporal Grounding (TG) aims to localize video segments corresponding to a textual query. Prior research predominantly focuses on single-segment retrieval. Real-world scenarios, ho…
MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging
Siyuan Li, Kai Yu, Anna Wang +7
Modeling genomic sequences faces two unsolved challenges: the information density varies widely across different regions, while there is no clearly defined minimum vocabulary unit.…
GLEAM: Learning to Match and Explain in Cross-View Geo-Localization
Xudong Lu, Zhi Zheng, Yi Wan +11
Cross-View Geo-Localization (CVGL) focuses on identifying correspondences between images captured from distinct perspectives of the same geographical location. However, existing CV…
Evaluating Compositional Scene Understanding in Multimodal Generative Models
Shuhao Fu, Andrew Jun Lee, Anna Wang +4
The visual world is fundamentally compositional. Visual scenes are defined by the composition of objects and their relations. Hence, it is essential for computer vision systems to…
DSCLAP: Domain-Specific Contrastive Language-Audio Pre-Training
Shengqiang Liu, Da Liu, Anna Wang +3
Analyzing real-world multimodal signals is an essential and challenging task for intelligent voice assistants (IVAs). Mainstream approaches have achieved remarkable performance on…
MV: A multi-modal multi-view approach for Device-Directed Speech Detection
Anna Wang, Da Liu, Zhiyu Zhang +3
With the goal of more natural and human-like interaction with virtual voice assistants, recent research in the field has focused on full duplex interaction mode without relying on…
Turbo your multi-modal classification with contrastive learning
Zhiyu Zhang, Da Liu, Shengqiang Liu +3
Contrastive learning has become one of the most impressive approaches for multi-modal representation learning. However, previous multi-modal works mainly focused on cross-modal und…