5 citations · 6 across the 5 of their papers we have counts for
5 papers · 1 filter
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:…
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…
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…
Pair-wise Layer Attention with Spatial Masking for Video Prediction
Ping Li, Chenhan Zhang, Zheng Yang +2
Video prediction yields future frames by employing the historical frames and has exhibited its great potential in many applications, e.g., meteorological prediction, and autonomous…
Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation
Ping Li, Junjie Chen, Li Yuan +2
To alleviate the expensive human labeling, semi-supervised semantic segmentation employs a few labeled images and an abundant of unlabeled images to predict the pixel-level label m…