Celso M. de Melo

8 papers · 2022–2026 · 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird 🔥 Unstoppable · Bronze

Venues

CVPR (3) WACV (3) AAAI (1) ECCV (1)

Top co-authors

Rama Chellappa (3) Ketul Shah (2) Arun Reddy (2) Vishal M. Patel (2) Po-Yao Huang (1) Suya You (1) Anshul Shah (1) Alexander G. Hauptmann (1) Benjamin Van Durme (1) Vibashan VS (1)

Research topics

Machine Learning (6) Computer Vision (5) Deep Learning (4) Analysis (4) Artificial Intelligence (3) Application Areas (3) Learning Types · Machine Learning (3) Architectures (2) Core AI (2) Core Methods (2) Domain-Specific (2) Learning Types · Deep Learning (2) Learning Paradigms (1) Processing (1)

Keywords

domain generalization (2) action recognition (2) self-supervised learning (2) change detection (1) knowledge distillation (1) supervised learning (1) cross-modal learning (1) feature embedding (1) human pose estimation (1) unsupervised domain adaptation (1) deep learning (1) remote sensing (1) motion capture (1) multi-view learning (1) group activity recognition (1) diffusion model (1) open-set learning (1) self-supervised pretraining (1) visual prompt (1) spatial-temporal modeling (1)

Papers

PromptGAR: Flexible Promptive Group Activity Recognition WACV 2026 Referring Change Detection in Remote Sensing Imagery WACV 2026 Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval CVPR 2025 Entropic Open-Set Active Learning AAAI 2024 Unsupervised Video Domain Adaptation with Masked Pre-Training and Collaborative Self-Training CVPR 2024 Multi-View Action Recognition Using Contrastive Learning WACV 2023 STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition CVPR 2023 Not Just Streaks: Towards Ground Truth for Single Image Deraining ECCV 2022