3 papers
cs.CV2026
Channel-wise Dynamic Knowledge Distillation via Adaptive Sample Generation for Action Recognition
Ping Li, Chenhao Ping, Jie Song +1
Knowledge Distillation (KD) offers a promising yet underexplored path for compressing large action recognition models. However, existing KD methods suffer from two key limitations:…
cs.CV2025
Sample-level Adaptive Knowledge Distillation for Action Recognition
Ping Li, Chenhao Ping, Wenxiao Wang +1
Knowledge Distillation (KD) compresses neural networks by learning a small network (student) via transferring knowledge from a pre-trained large network (teacher). Many endeavours…
cs.CV2024
Pseudo-labeling with Keyword Refining for Few-Supervised Video Captioning
Ping Li, Tao Wang, Xinkui Zhao +2
Video captioning generate a sentence that describes the video content. Existing methods always require a number of captions (\eg, 10 or 20) per video to train the model, which is q…