Action Recognition

Scattered Online Inference (SOI) drastically cuts down ANN computational complexity by leveraging data continuity and prediction seasonality, enabling faster real-time inference on low-power devices.

Boost skeleton action recognition accuracy across datasets by recovering complete actions and resampling; outperforms existing methods.

Deep neural networks finally match human biological motion perception capabilities by leveraging patch-level optical flows and innovative neuron designs, achieving a 29% accuracy improvement.

Zero-shot online action detection gets a boost! OV-OAD leverages vision-language models and text supervision to achieve impressive performance on various benchmarks without relying on manual annotati…

CHASE: A novel method for skeleton-based multi-entity action recognition that cleverly adapts skeleton positions to minimize data bias and boost accuracy.

ActFusion: a unified diffusion model achieving state-of-the-art performance in both action segmentation and anticipation by jointly learning visible and invisible parts of video sequences.