most citedVideo + CLIP Baseline for Ego4D Long-term Action Anticipation

7 citations · 9 across the 2 of their papers we have counts for

collaborators

5 papers

cs.CV2023

Attention De-sparsification Matters: Inducing Diversity in Digital Pathology Representation Learning

Saarthak Kapse, Srijan Das, Jingwei Zhang +4

We propose DiRL, a Diversity-inducing Representation Learning technique for histopathology imaging. Self-supervised learning techniques, such as contrastive and non-contrastive app…

cs.CV2023

AAN: Attributes-Aware Network for Temporal Action Detection

Rui Dai, Srijan Das, Michael S. Ryoo +1

The challenge of long-term video understanding remains constrained by the efficient extraction of object semantics and the modelling of their relationships for downstream tasks. Al…

cs.CV2023

Attending Generalizability in Course of Deep Fake Detection by Exploring Multi-task Learning

Pranav Balaji, Abhijit Das, Srijan Das +1

This work explores various ways of exploring multi-task learning (MTL) techniques aimed at classifying videos as original or manipulated in cross-manipulation scenario to attend ge…

cs.CV20227 cited

Video + CLIP Baseline for Ego4D Long-term Action Anticipation

Srijan Das, Michael S. Ryoo

In this report, we introduce our adaptation of image-text models for long-term action anticipation. Our Video + CLIP framework makes use of a large-scale pre-trained paired image-t…

cs.CV20212 cited

ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints

Srijan Das, Michael S. Ryoo

Learning self-supervised video representation predominantly focuses on discriminating instances generated from simple data augmentation schemes. However, the learned representation…