Jathushan Rajasegaran
12 papers · 2019–2026 · 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 ↓+4 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (30)
🧬
Topic Evolution
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
🗃️
Keyword Collector
(75)
Venues
Top co-authors
Research topics
Computer Vision
(8)
Deep Learning
(8)
Analysis
(8)
Learning Types · Deep Learning
(5)
Machine Learning
(4)
Architectures
(4)
Learning Types · Machine Learning
(4)
Core Methods
(3)
Artificial Intelligence
(2)
Models
(2)
Processing
(2)
Core AI
(1)
Learning Paradigms · Artificial Intelligence
(1)
Learning Paradigms · Machine Learning
(1)
Keywords
representation learning
(3)
object tracking
(3)
transformer architecture
(3)
incremental learning
(2)
pose estimation
(2)
catastrophic forgetting
(2)
video understanding
(2)
convolutional neural network
(2)
3d reconstruction
(2)
human mesh recovery
(2)
3d pose estimation
(2)
video representation learning
(2)
autoregressive model
(2)
self-supervised learning
(1)
visual perception
(1)
temporal modeling
(1)
continual learning
(1)
action recognition
(1)
image segmentation
(1)
image reconstruction
(1)
Papers
Tracking by Predicting 3-D Gaussians Over Time
CVPR 2026
An Empirical Study of Autoregressive Pre-training from Videos
ICCV 2025
Scaling Properties of Diffusion Models For Perceptual Tasks
CVPR 2025
EgoPet: Egomotion and Interaction Data from an Animal's Perspective
ECCV 2024
Humanoid Locomotion as Next Token Prediction
NeurIPS 2024
Humans in 4D: Reconstructing and Tracking Humans with Transformers
ICCV 2023
On the Benefits of 3D Pose and Tracking for Human Action Recognition
CVPR 2023
Tracking People by Predicting 3D Appearance, Location and Pose
CVPR 2022
Tracking People with 3D Representations
NeurIPS 2021
iTAML: An Incremental Task-Agnostic Meta-learning Approach
CVPR 2020
DeepCaps: Going Deeper With Capsule Networks
CVPR 2019
Random Path Selection for Continual Learning
NeurIPS 2019