Mehdi S. M. Sajjadi
22 papers · 2017–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (6) π Academic Marathon (8) π Renaissance Researcher (6) πΊοΈ Taxonomy Completionist (40)
πΊοΈ
Taxonomy Completionist
(40)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π§¬
Topic Evolution
π₯
Mega-Team
(34)
π
Century Club
(22)
ποΈ
Keyword Collector
(78)
π
Conference Pioneer
π₯
Unstoppable
(6)
π
Trend Setter
Conferences
CVPR (6)
ICML (5)
ICCV (4)
ICLR (3)
NIPS (3)
ECCV (1)
Top co-authors
Keywords
3d reconstruction
(5)
novel view synthesis
(5)
self-supervised learning
(4)
scene representation
(3)
depth estimation
(2)
video understanding
(2)
representation learning
(2)
video representation
(2)
photorealistic rendering
(2)
vision transformer
(2)
generative adversarial network
(2)
neural radiance field
(2)
slot attention
(2)
test-time adaptation
(1)
pose estimation
(1)
multimodal learning
(1)
action recognition
(1)
out-of-distribution generalization
(1)
data annotation
(1)
embodied ai
(1)
Papers
Direct Motion Models for Assessing Generated Videos
ICML 2025
From Image to Video: An Empirical Study of Diffusion Representations
ICCV 2025
TAPNext: Tracking Any Point (TAP) as Next Token Prediction
ICCV 2025
LayerLock: Non-collapsing Representation Learning with Progressive Freezing
ICCV 2025
DyST: Towards Dynamic Neural Scene Representations on Real-World Videos
ICLR 2024
Moving Off-the-Grid: Scene-Grounded Video Representations
NIPS 2024
DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$
ICLR 2024
PaLM-E: An Embodied Multimodal Language Model
ICML 2023
RUST: Latent Neural Scene Representations From Unposed Imagery
CVPR 2023
Test-time Adaptation with Slot-Centric Models
ICML 2023
Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames
ICML 2023
Kubric: A Scalable Dataset Generator
CVPR 2022
Object Scene Representation Transformer
NIPS 2022
Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations
CVPR 2022
RegNeRF: Regularizing Neural Radiance Fields for View Synthesis From Sparse Inputs
CVPR 2022
NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections
CVPR 2021
From Variational to Deterministic Autoencoders
ICLR 2020
Frame-Recurrent Video Super-Resolution
CVPR 2018
Spatio-temporal Transformer Network for Video Restoration
ECCV 2018
Assessing Generative Models via Precision and Recall
NIPS 2018
Tempered Adversarial Networks
ICML 2018
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
ICCV 2017