Pavel Tokmakov
21 papers · 2017–2025 · 5 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (34) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Keyword Champion
(3)
π§¬
Topic Evolution
π
Trend Setter
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(92)
Top co-authors
Research topics
Computer Vision
(15)
Analysis
(12)
Deep Learning
(10)
Processing
(8)
Machine Learning
(6)
Learning Types Β· Machine Learning
(6)
Learning Types Β· Deep Learning
(5)
Artificial Intelligence
(4)
Core AI
(4)
Core Methods
(4)
Models
(4)
Architectures
(3)
Generation
(2)
Natural Language Processing
(1)
Applications
(1)
Keywords
video segmentation
(4)
multi-object tracking
(3)
motion segmentation
(3)
occlusion handling
(3)
video understanding
(3)
object permanence
(3)
semantic segmentation
(3)
3d reconstruction
(2)
diffusion model
(2)
novel view synthesis
(2)
object tracking
(2)
zero-shot learning
(2)
self-supervised learning
(2)
object segmentation
(2)
embedding learning
(1)
object detection
(1)
metric learning
(1)
similarity learning
(1)
image segmentation
(1)
computer vision
(1)
Papers
ReferEverything: Towards Segmenting Everything We Can Speak of in Videos
ICCV 2025
Robust Multi-Object 4D Generation for In-the-wild Videos
CVPR 2025
Understanding Complexity in VideoQA via Visual Program Generation
ICML 2025
Dreamitate: Real-World Visuomotor Policy Learning via Video Generation
CoRL 2024
Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis
ECCV 2024
pix2gestalt: Amodal Segmentation by Synthesizing Wholes
CVPR 2024
Understanding Video Transformers via Universal Concept Discovery
CVPR 2024
Breaking the "Object" in Video Object Segmentation
CVPR 2023
Object Discovery From Motion-Guided Tokens
CVPR 2023
Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking
CVPR 2023
Tracking Through Containers and Occluders in the Wild
CVPR 2023
Zero-1-to-3: Zero-shot One Image to 3D Object
ICCV 2023
Discovering Objects That Can Move
CVPR 2022
Object Permanence Emerges in a Random Walk along Memory
ICML 2022
Learning To Track With Object Permanence
ICCV 2021
TAO: A Large-Scale Benchmark for Tracking Any Object
ECCV 2020
A Structured Model for Action Detection
CVPR 2019
Learning Compositional Representations for Few-Shot Recognition
ICCV 2019
Towards Latent Attribute Discovery From Triplet Similarities
ICCV 2019
Learning Motion Patterns in Videos
CVPR 2017
Learning Video Object Segmentation With Visual Memory
ICCV 2017