Track and Caption Any Motion: Open-Vocabulary Spatiotemporal Captioning via Trajectory-Conditioned Generation
Paper • 2512.10607 • Published
AI & ML interests
None defined yet.
Recent Activity
Papers
Motion-o: Trajectory-Grounded Video Reasoning
HORNet: Task-Guided Frame Selection for Video Question Answering with Vision-Language Models
bishoygaloaaÂ
authored 5
papers 4 days ago
ViMoLa: Discrete Motion Tokens for Language-Guided Video Generation
Paper • 2610.25595 • Published
PanoWorld: Geometry-Consistent Panoramic Video World Modeling
Paper • 2605.15391 • Published
Lang2Motion: Bridging Language and Motion through Joint Embedding Spaces
Paper • 2512.10617 • Published
MoReGen: Multi-Agent Motion-Reasoning Engine for Code-based Text-to-Video Synthesis
Paper • 2512.04221 • Published
bishoygaloaaÂ
authored a
paper about 1 month ago
bishoygaloaaÂ
updated a
dataset about 1 month ago
[bot] Conversion to Parquet
#1 opened 2 months ago
by 
parquet-converter
bishoygaloaaÂ
published a
dataset 2 months ago
bishoygaloaaÂ
authored a
paper 3 months ago
smoezziÂ
authored a
paper 6 months ago
bishoygaloaaÂ
updated a
dataset 6 months ago
bishoygaloaaÂ
published a
dataset 6 months ago
bishoygaloaaÂ
updated a
Space 6 months ago
bishoygaloaaÂ
published a
Space 6 months ago
bishoygaloaaÂ
authored 3
papers 7 months ago
Structured Over Scale: Learning Spatial Reasoning from Educational Video
Paper • 2601.23251 • Published • 1
HORNet: Task-Guided Frame Selection for Video Question Answering with Vision-Language Models
Paper • 2603.18850 • Published • 1
Motion-o: Trajectory-Grounded Video Reasoning
Paper • 2603.18856 • Published • 2