2 papers
cs.CV2025
SGCap: Decoding Semantic Group for Zero-shot Video Captioning
Zeyu Pan, Ping Li, Wenxiao Wang
Zero-shot video captioning aims to generate sentences for describing videos without training the model on video-text pairs, which remains underexplored. Existing zero-shot image ca…
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…