2 papers
cs.CV2025
Supervised Contrastive Frame Aggregation for Video Representation Learning
Shaif Chowdhury, Mushfika Rahman, Greg Hamerly
We propose a supervised contrastive learning framework for video representation learning that leverages temporally global context. We introduce a video to image aggregation strateg…
cs.LG2025
Effective Fine-Tuning with Eigenvector Centrality Based Pruning
Shaif Chowdhury, Soham Biren Katlariwala, Devleena Kashyap
In social media networks a small number of highly influential users can drive large scale changes in discourse across multiple communities. Small shifts in the behavior of these us…