149 citations · 278 across the 55 of their papers we have counts for
71 papers
Re:Cognize -- A Framework For Open-Set Comic Character Re-Identification
Aaditya Baranwal, Madhav Kataria, Yogesh S Rawat +1
Comics and manga tell stories through characters whose appearances change from panel to panel, yet readers recognise them hundreds of pages later without ever consulting a cast lis…
Position Aware Layer Queries for Test Time Training in Vision Language Models
Rajat Modi, Priyank Pathak, Xin Liang +1
Test-Time Training (TTT) adapts models to incoming test samples (e.g. out-of-distribution, (OOD)) when conventional fine-tuning is infeasible. Existing TTT methods for Vision-Langu…
Modern GLOM: Canonical locks that encode part-whole hierarchies
Rajat Modi, Yogesh Singh Rawat
One of the challenges in representational learning is how to encode part-whole hierarchies in a neural net. Prior works rely on flattening tree-like structures into string-like seq…
A Generative Approach for Improving Multi-Label Defect Classification in Photovoltaic Modules
Abdul Mueez, Yogesh S. Rawat, Shruti Vyas
This paper addresses the challenge of multi-label defect classification in electroluminescence (EL) images of photovoltaic (PV) cells. Training models on images where multiple defe…
Forget, Anticipate and Adapt: Test Time Training for Long Videos
Rajat Modi, Sebastian Noel, Xin Liang +1
Test Time Training (TTT) is a mechanism in which a model adapts to an incoming test-sample by performing some self-supervised (SSL) task and updating its weights even during infere…
Learning to Deny: Action Denial in Multimodal Large Language Models
Raiyaan Abdullah, Shehreen Azad, Yogesh Singh Rawat
Multimodal large language models (MLLMs) have rapidly advanced video understanding, achieving strong zero-shot and few-shot recognition across standard benchmarks. Yet their abilit…
Robust Onion: Peeling Open Vocab Object Detectors Under Noise
Priyank Pathak, Mukilan Karuppasamy, Aaditya Baranwal +2
The impact of real-world noise on Open Vocabulary Object Detectors (OV-ODs) remains poorly understood due to their architectural complexity. We present our comprehensive analysis R…
MolSight: Molecular Property Prediction with Images
Aaditya Baranwal, Akshaj Gupta, Yogesh S Rawat +1
Every molecule ever synthesised can be drawn as a 2D skeletal diagram, yet in modern property prediction this universally available representation has received less focus in favour…
VISTA: Video Interaction Spatio-Temporal Analysis Benchmark
Alejandro Aparcedo, Akash Kumar, Aaryan Garg +5
Existing benchmarks for Vision-Language Models (VLMs) primarily evaluate spatio-temporal understanding on simple single-action videos, closed attribute sets and restricted entity t…
Sky2Ground: A Benchmark for Site Modeling under Varying Altitude
Zengyan Wang, Sirshapan Mitra, Rajat Modi +2
We introduce Sky2Ground, a three-view dataset designed for varying altitude camera localization, correspondence learning, and reconstruction. The dataset combines structured synthe…
ProDiG: Progressive Diffusion-Guided Gaussian Splatting for Aerial to Ground Reconstruction
Sirshapan Mitra, Yogesh S. Rawat
Generating ground-level views and coherent 3D site models from aerial-only imagery is challenging due to extreme viewpoint changes, missing intermediate observations, and large sca…
VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
Chaoyang Wang, Wenrui Bao, Sicheng Gao +5
Vision-Language-Action (VLA) models have shown promising capabilities for embodied intelligence, but most existing approaches rely on text-based chain-of-thought reasoning where vi…
StreamReady: Learning What to Answer and When in Long Streaming Videos
Shehreen Azad, Vibhav Vineet, Yogesh Singh Rawat
Streaming video understanding often involves time-sensitive scenarios where models need to answer exactly when the supporting visual evidence appears: answering before the evidence…
CoSPlan: Corrective Sequential Planning via Scene Graph Incremental Updates
Shresth Grover, Priyank Pathak, Akash Kumar +1
Vision Language Models (VLMs) have shown promising planning capabilities, yet their success remains confined to the text domain, leaving visual decision-making relatively underexpl…
RobustGait: Robustness Analysis for Appearance Based Gait Recognition
Reeshoon Sayera, Akash Kumar, Sirshapan Mitra +2
Appearance-based gait recognition have achieved strong performance on controlled datasets, yet systematic evaluation of its robustness to real-world corruptions and silhouette vari…
OmViD: Omni-supervised active learning for video action detection
Aayush Rana, Akash Kumar, Vibhav Vineet +1
Video action detection requires dense spatio-temporal annotations, which are both challenging and expensive to obtain. However, real-world videos often vary in difficulty and may n…
GaitCrafter: Diffusion Model for Biometric Preserving Gait Synthesis
Sirshapan Mitra, Yogesh S. Rawat
Gait recognition is a valuable biometric task that enables the identification of individuals from a distance based on their walking patterns. However, it remains limited by the lac…
Re:Verse -- Can Your VLM Read a Manga?
Aaditya Baranwal, Madhav Kataria, Naitik Agrawal +2
Current Vision Language Models (VLMs) demonstrate a critical gap between surface-level recognition and deep narrative reasoning when processing sequential visual storytelling. Thro…
iSafetyBench: A video-language benchmark for safety in industrial environment
Raiyaan Abdullah, Yogesh Singh Rawat, Shruti Vyas
Recent advances in vision-language models (VLMs) have enabled impressive generalization across diverse video understanding tasks under zero-shot settings. However, their capabiliti…
Punching Bag vs. Punching Person: Motion Transferability in Videos
Raiyaan Abdullah, Jared Claypoole, Michael Cogswell +2
Action recognition models demonstrate strong generalization, but can they effectively transfer high-level motion concepts across diverse contexts, even within similar distributions…
DisenQ: Disentangling Q-Former for Activity-Biometrics
Shehreen Azad, Yogesh S Rawat
In this work, we address activity-biometrics, which involves identifying individuals across diverse set of activities. Unlike traditional person identification, this setting introd…
Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement
Priyank Pathak, Yogesh S. Rawat
Clothes-Changing Re-Identification (CC-ReID) aims to recognize individuals across different locations and times, irrespective of clothing. Existing methods often rely on additional…
MolVision: Molecular Property Prediction with Vision Language Models
Deepan Adak, Yogesh Singh Rawat, Shruti Vyas
Molecular property prediction is a fundamental task in computational chemistry with critical applications in drug discovery and materials science. While recent works have explored…
Coarse Attribute Prediction with Task Agnostic Distillation for Real World Clothes Changing ReID
Priyank Pathak, Yogesh S Rawat
This work focuses on Clothes Changing Re-IDentification (CC-ReID) for the real world. Existing works perform well with high-quality (HQ) images, but struggle with low-quality (LQ)…