Yogesh S Rawat
13 papers · 2020–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (7) π Academic Marathon (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (23)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Century Club
(13)
Conferences
CVPR (4)
ICLR (3)
ECCV (2)
AAAI (1)
EMNLP (1)
NIPS (1)
WACV (1)
Top co-authors
Keywords
video understanding
(3)
action recognition
(2)
self-supervised learning
(1)
video segmentation
(1)
person re-identification
(1)
attention mechanism
(1)
knowledge distillation
(1)
weakly supervised learning
(1)
prompt engineering
(1)
multi-label classification
(1)
image generation
(1)
adversarial learning
(1)
feature disentanglement
(1)
progressive learning
(1)
spatio-temporal localization
(1)
diffusion model
(1)
large multimodal model
(1)
end-to-end learning
(1)
vision-language model
(1)
zero-shot learning
(1)
Papers
RobustGait: Robustness Analysis for Appearance Based Gait Recognition
WACV 2026
STPro: Spatial and Temporal Progressive Learning for Weakly Supervised Spatio-Temporal Grounding
CVPR 2025
Contextual Self-paced Learning for Weakly Supervised Spatio-Temporal Video Grounding
ICLR 2025
LR0.FM: Low-Res Benchmark and Improving robustness for Zero-Shot Classification in Foundation Models
ICLR 2025
DIFFER: Disentangling Identity Features via Semantic Cues for Clothes-Changing Person Re-ID
CVPR 2025
AirSketch: Generative Motion to Sketch
NIPS 2024
Navigating Hallucinations for Reasoning of Unintentional Activities
EMNLP 2024
SSA2D: Single Shot Actor-Action Detection in Videos (Student Abstract)
AAAI 2021
In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
ICLR 2021
Modeling Multi-Label Action Dependencies for Temporal Action Localization
CVPR 2021
Multi-view Action Recognition using Cross-view Video Prediction
ECCV 2020
Visual-Textual Capsule Routing for Text-Based Video Segmentation
CVPR 2020
A Recurrent Transformer Network for Novel View Action Synthesis
ECCV 2020