Kumar Ashutosh

11 papers · 2021–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+3 more ↓

🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (30)

👥 Mega-Team · Civilization 💎 Century Club · Bronze 🗃️ Keyword Collector (70)

Venues

CVPR (8) AISTATS (1) ICML (1) NeurIPS (1)

Top co-authors

Kristen Grauman (9) Zihui Xue (3) Tushar Nagarajan (3) Rohit Girdhar (3) Triantafyllos Afouras (2) Kris Kitani (2) Santhosh Kumar Ramakrishnan (2) Changan Chen (2) Lorenzo Torresani (2) Georgios Pavlakos (2)

Research topics

Artificial Intelligence (9) Core AI · Artificial Intelligence (9) Computer Vision (8) Machine Learning (8) Learning Types · Machine Learning (6) Processing (6) Deep Learning (5) Core AI · Computer Vision (5) Analysis (3) Learning Types · Deep Learning (3) Natural Language Processing (2) Architectures (2) Domain-Specific (2) Models (2) Optimization & Theory (2)

Keywords

video understanding (4) instructional video (3) multimodal learning (3) egocentric vision (2) zero-shot learning (2) contrastive learning (2) action recognition (2) egocentric video (2) weakly supervised learning (2) video retrieval (2) self-supervised learning (1) pose estimation (1) weak supervision (1) human-object interaction (1) audio-visual learning (1) text-to-image generation (1) future prediction (1) hand pose estimation (1) 3d scene understanding (1) question answering (1)

Papers

Stitch-a-Demo: Creating Video Demonstrations from Multistep Descriptions CVPR 2026 ExpertAF: Expert Actionable Feedback from Video CVPR 2025 FIction: 4D Future Interaction Prediction from Video CVPR 2025 LLMs can see and hear without any training ICML 2025 Detours for Navigating Instructional Videos CVPR 2024 Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives CVPR 2024 Learning Object State Changes in Videos: An Open-World Perspective CVPR 2024 SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos CVPR 2024 HierVL: Learning Hierarchical Video-Language Embeddings CVPR 2023 Video-Mined Task Graphs for Keystep Recognition in Instructional Videos NeurIPS 2023 Bandit algorithms: Letting go of logarithmic regret for statistical robustness AISTATS 2021