Shraman Pramanick

6

Papers

50

Total Citations

1

Affiliations

Affiliations

Johns Hopkins University

Papers (6)

Jack of All Tasks Master of Many: Designing General-Purpose Coarse-to-Fine Vision-Language Model

Enrich and Detect: Video Temporal Grounding with Multimodal LLMs

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

UniVTG: Towards Unified Video-Language Temporal Grounding

EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone

Where in the World Is This Image? Transformer-Based Geo-Localization in the Wild