Tomáš Souček
4 papers · 2022–2025 · 2 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
self-supervised learning
(2)
pose estimation
(1)
video understanding
(1)
object tracking
(1)
trajectory optimization
(1)
video diffusion model
(1)
causal ordering
(1)
temporal localization
(1)
visual instruction
(1)
image sequence generation
(1)
object state
(1)
cad model retrieval
(1)
state-modifying action
(1)
step-by-step generation
(1)
robotic manipulation
(1)
6d object pose
(1)
Papers
6D Object Pose Tracking in Internet Videos for Robotic Manipulation
ICLR 2025
ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions
CVPR 2025
GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos
CVPR 2024
Look for the Change: Learning Object States and State-Modifying Actions From Untrimmed Web Videos
CVPR 2022