5 papers
Image Classifiers are Efficient Self-Supervised Video Representation Learners
Owais Iqbal, Sudipta Sarkar, Shyam Marjit +3
We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of relying on heavy 3D architectu…
DynEval: Holistic Evaluations of T2I Generative Models in the Wild
Shyam Marjit, Dheeraj Baiju, Anuj Shikarkhane +3
Recent advances in text-to-image (T2I) generation have led to models capable of producing highly realistic images. Yet, reliably evaluating their outputs remains challenging, espec…
O3SLM: Open Weight, Open Data, and Open Vocabulary Sketch-Language Model
Rishi Gupta, Mukilan Karuppasamy, Shyam Marjit +2
While Large Vision Language Models (LVLMs) are increasingly deployed in real-world applications, their ability to interpret abstract visual inputs remains limited. Specifically, th…
Prompt Estimation from Prototypes for Federated Prompt Tuning of Vision Transformers
M Yashwanth, Sharannya Ghosh, Aditay Tripathi +1
Visual Prompt Tuning (VPT) of pre-trained Vision Transformers (ViTs) has proven highly effective as a parameter-efficient fine-tuning technique for adapting large models to downstr…
Sketch-guided Image Inpainting with Partial Discrete Diffusion Process
Nakul Sharma, Aditay Tripathi, Anirban Chakraborty +1
In this work, we study the task of sketch-guided image inpainting. Unlike the well-explored natural language-guided image inpainting, which excels in capturing semantic details, th…