Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition
Shristi Das Biswas, Efstathia Soufleri, Arani Roy +1
Training robust deep video representations has proven to be computationally challenging due to substantial decoding overheads, the enormous size of raw video streams, and their inh…
cs.CV2024
Advancing Compressed Video Action Recognition through Progressive Knowledge Distillation
Efstathia Soufleri, Deepak Ravikumar, Kaushik Roy
Compressed video action recognition classifies video samples by leveraging the different modalities in compressed videos, namely motion vectors, residuals, and intra-frames. For th…