Alert button
Picture for Srijan Das

Srijan Das

Alert button

Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space

Jun 23, 2022
Jinghuan Shang, Srijan Das, Michael S. Ryoo

Figure 1 for Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
Figure 2 for Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
Figure 3 for Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
Figure 4 for Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
Viaarxiv icon

Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?

Jun 23, 2022
Xiang Li, Jinghuan Shang, Srijan Das, Michael S. Ryoo

Figure 1 for Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
Figure 2 for Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
Figure 3 for Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
Figure 4 for Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
Viaarxiv icon

CD-Net: Histopathology Representation Learning using Pyramidal Context-Detail Network

Mar 28, 2022
Saarthak Kapse, Srijan Das, Prateek Prasanna

Figure 1 for CD-Net: Histopathology Representation Learning using Pyramidal Context-Detail Network
Figure 2 for CD-Net: Histopathology Representation Learning using Pyramidal Context-Detail Network
Figure 3 for CD-Net: Histopathology Representation Learning using Pyramidal Context-Detail Network
Figure 4 for CD-Net: Histopathology Representation Learning using Pyramidal Context-Detail Network
Viaarxiv icon

STC-mix: Space, Time, Channel mixing for Self-supervised Video Representation

Dec 07, 2021
Srijan Das, Michael S. Ryoo

Figure 1 for STC-mix: Space, Time, Channel mixing for Self-supervised Video Representation
Figure 2 for STC-mix: Space, Time, Channel mixing for Self-supervised Video Representation
Figure 3 for STC-mix: Space, Time, Channel mixing for Self-supervised Video Representation
Figure 4 for STC-mix: Space, Time, Channel mixing for Self-supervised Video Representation
Viaarxiv icon

ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints

Dec 07, 2021
Srijan Das, Michael S. Ryoo

Figure 1 for ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
Figure 2 for ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
Figure 3 for ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
Figure 4 for ViewCLR: Learning Self-supervised Video Representation for Unseen Viewpoints
Viaarxiv icon

MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection

Dec 07, 2021
Rui Dai, Srijan Das, Kumara Kahatapitiya, Michael S. Ryoo, Francois Bremond

Figure 1 for MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
Figure 2 for MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
Figure 3 for MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
Figure 4 for MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
Viaarxiv icon

CTRN: Class-Temporal Relational Network for Action Detection

Oct 26, 2021
Rui Dai, Srijan Das, Francois Bremond

Figure 1 for CTRN: Class-Temporal Relational Network for Action Detection
Figure 2 for CTRN: Class-Temporal Relational Network for Action Detection
Figure 3 for CTRN: Class-Temporal Relational Network for Action Detection
Figure 4 for CTRN: Class-Temporal Relational Network for Action Detection
Viaarxiv icon

Weakly-supervised Joint Anomaly Detection and Classification

Aug 20, 2021
Snehashis Majhi, Srijan Das, Francois Bremond, Ratnakar Dash, Pankaj Kumar Sa

Figure 1 for Weakly-supervised Joint Anomaly Detection and Classification
Figure 2 for Weakly-supervised Joint Anomaly Detection and Classification
Figure 3 for Weakly-supervised Joint Anomaly Detection and Classification
Figure 4 for Weakly-supervised Joint Anomaly Detection and Classification
Viaarxiv icon

Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection

Aug 08, 2021
Rui Dai, Srijan Das, Francois Bremond

Figure 1 for Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection
Figure 2 for Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection
Figure 3 for Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection
Figure 4 for Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection
Viaarxiv icon

VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living

May 17, 2021
Srijan Das, Rui Dai, Di Yang, Francois Bremond

Figure 1 for VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
Figure 2 for VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
Figure 3 for VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
Figure 4 for VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
Viaarxiv icon