Shyamal Buch
14 papers · 2017–2026 · 6 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 ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (34)
π§¬
Topic Evolution
π
Century Club Β· Bronze
π
Conference Pioneer
ποΈ
Keyword Collector
(65)
Top co-authors
Research topics
Artificial Intelligence
(9)
Core AI Β· Artificial Intelligence
(9)
Computer Vision
(8)
Processing
(7)
Deep Learning
(5)
Machine Learning
(5)
Learning Types Β· Deep Learning
(4)
Natural Language Processing
(3)
Application Areas
(3)
Learning Types Β· Machine Learning
(3)
Architectures
(2)
Core AI Β· Computer Vision
(2)
Core Methods
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Keywords
video understanding
(6)
multimodal learning
(4)
video reasoning
(3)
video question answering
(3)
efficient computing
(2)
temporal reasoning
(1)
weakly supervised learning
(1)
visual question answering
(1)
visual reasoning
(1)
temporal alignment
(1)
visual grounding
(1)
embodied ai
(1)
natural language queries
(1)
efficient inference
(1)
self-supervised learning
(1)
event detection
(1)
activity recognition
(1)
egocentric vision
(1)
multiple instance learning
(1)
video captioning
(1)
Papers
Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding
CVPR 2026
Flexible Frame Selection for Efficient Video Reasoning
CVPR 2025
MINERVA: Evaluating Complex Video Reasoning
ICCV 2025
OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption Models
EMNLP 2025
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
NeurIPS 2024
MoReVQA: Exploring Modular Reasoning Models for Video Question Answering
CVPR 2024
Streaming Dense Video Captioning
CVPR 2024
Streaming Detection of Queried Event Start
NeurIPS 2024
Revisiting the "Video" in Video-Language Understanding
CVPR 2022
BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments
CoRL 2021
RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition
ECCV 2020
End-to-End Joint Semantic Segmentation of Actors and Actions in Video
ECCV 2018
Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos
CVPR 2018
SST: Single-Stream Temporal Action Proposals
CVPR 2017