3 papers
cs.CV2026
GeoTrace: Geometry-Aware Trajectory Token Compression for Video Large Language Models
Guohuan Xie, Mengqi Lei, Chuan Shi +3
Although Video Large Language Models (Video LLMs) have shown strong performance in video understanding, their efficiency is still limited by the large number of visual tokens. Exis…
cs.CV2026
M^2C-EvDet: Multi-Domain Multi-Order Cross-Modal Knowledge Distillation for Event-based Object Detection
Wei Bao, Siqi Li, Shouan Pan +2
Event-based object Detection (EvDet), as a biologically inspired visual perception paradigm, demonstrates superior performance in scenarios demanding high temporal resolution and a…
cs.CV2025
FineSkiing: A Fine-grained Benchmark for Skiing Action Quality Assessment
Yongji Zhang, Siqi Li, Yue Gao +1
Action Quality Assessment (AQA) aims to evaluate and score sports actions, which has attracted widespread interest in recent years. Existing AQA methods primarily predict scores ba…