activity
20222026
most citedLearning Implicit Representation for Reconstructing Articulated Objects

1 citations · 1 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

Finding Distributed Object-Centric Properties in Self-Supervised Transformers

Samyak Rawlekar, Amitabh Swain, Yujun Cai +3

Self-supervised Vision Transformers (ViTs) like DINO show an emergent ability to discover objects, typically observed in [CLS] token attention maps of the final layer. However, the…

cs.CV2025

Efficiently Disentangling CLIP for Multi-Object Perception

Samyak Rawlekar, Yujun Cai, Yiwei Wang +2

Vision-language models like CLIP excel at recognizing the single, prominent object in a scene. However, they struggle in complex scenes containing multiple objects. We identify a f…

cs.CV2024

Rethinking Prompting Strategies for Multi-Label Recognition with Partial Annotations

Samyak Rawlekar, Shubhang Bhatnagar, Narendra Ahuja

Vision-language models (VLMs) like CLIP have been adapted for Multi-Label Recognition (MLR) with partial annotations by leveraging prompt-learning, where positive and negative prom…

cs.CV2024

S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video

Hao Zhang, Fang Li, Samyak Rawlekar +1

Reconstructing dynamic articulated objects from a singular monocular video is challenging, requiring joint estimation of shape, motion, and camera parameters from limited views. Cu…

cs.CV2024

Improving Multi-label Recognition using Class Co-Occurrence Probabilities

Samyak Rawlekar, Shubhang Bhatnagar, Vishnuvardhan Pogunulu Srinivasulu +1

Multi-label Recognition (MLR) involves the identification of multiple objects within an image. To address the additional complexity of this problem, recent works have leveraged inf…

cs.CV2024★ 1 cited

Learning Implicit Representation for Reconstructing Articulated Objects

Hao Zhang, Fang Li, Samyak Rawlekar +1

3D Reconstruction of moving articulated objects without additional information about object structure is a challenging problem. Current methods overcome such challenges by employin…