Thomas Lucas

14 papers · 2017–2025 · 7 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 ↓

+6 more ↓

🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🐣 Hot Topic Early Bird 🗺️ Taxonomy Completionist (21)

🧬 Topic Evolution 🧭 Keyword Pioneer 🤝 Dynamic Duo (11) 🏆 Grand Slam ⚡ Prolific Year · Productive 💎 Century Club · Bronze

Venues

ECCV (4) CVPR (2) ICCV (2) ICLR (2) NeurIPS (2) AAAI (1) ICML (1)

Top co-authors

Philippe Weinzaepfel (11) Gregory Rogez (5) Romain BRÉGIER (4) Vincent Leroy (4) Diane Larlus (3) Jerome Revaud (3) Yannis Kalantidis (3) Fabien Baradel (3) Jakob Verbeek (3) Matthieu Armando (2)

Research topics

Machine Learning (9) Deep Learning (8) Learning Types · Machine Learning (7) Computer Vision (5) Analysis (5) Application Areas (2) Architectures (2) Learning Types · Deep Learning (2) Models (2) Techniques (2) Core Methods (1)

Keywords

self-supervised learning (3) optical flow (2) cross-view completion (2) vision transformer (2) depth estimation (2) generative adversarial network (2) masked image modeling (2) data augmentation (1) semi-supervised learning (1) image classification (1) image retrieval (1) knowledge distillation (1) density estimation (1) semantic segmentation (1) stereo matching (1) transfer learning (1) efficient computing (1) 3d vision (1) optical flow estimation (1) few-shot learning (1)

Papers

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers CVPR 2025 Cross-view and Cross-pose Completion for 3D Human Understanding CVPR 2024 Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot ECCV 2024 UNIC: Universal Classification Models via Multi-teacher Distillation ECCV 2024 Win-Win: Training High-Resolution Vision Transformers from Two Windows ICLR 2024 CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow ICCV 2023 Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images AAAI 2022 CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion NeurIPS 2022 Learning Super-Features for Image Retrieval ICLR 2022 PoseGPT: Quantization-Based 3D Human Motion Generation and Forecasting ECCV 2022 PoseScript: 3D Human Poses from Natural Language ECCV 2022 Adaptive Density Estimation for Generative Models NeurIPS 2019 Mixed batches and symmetric discriminators for GAN training ICML 2018 Areas of Attention for Image Captioning ICCV 2017