Sergiu Nedevschi

7 papers · 2014–2025 · 3 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 🏃 Academic Marathon · Half 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) 📈 Trend Setter

Venues

CVPR (4) WACV (2) ICCV (1)

Top co-authors

Arthur Daniel Costea (3) Andra Petrovai (3) Radu Beche (1) Robert Varga (1)

Research topics

Computer Vision (7) Analysis (7) Deep Learning (3) Machine Learning (3) Learning Types · Machine Learning (3) Domain-Specific (2) Learning Types · Deep Learning (2) Processing (2) Architectures (1) Core Methods (1) Models (1)

Keywords

pedestrian detection (3) semantic segmentation (3) self-supervised learning (2) sliding window (2) depth estimation (2) video panoptic segmentation (2) monocular depth estimation (2) neural reconstruction (1) pseudo label (1) temporal consistency (1) panoptic segmentation (1) visual word (1) multimodal feature (1) scale invariance (1) geometric reconstruction (1) aerial imagery (1) depth prediction (1) photometric loss (1) instance tracking (1) transformer attention (1)

Papers

ClaraVid: A Holistic Scene Reconstruction Benchmark From Aerial Perspective With Delentropy-Based Complexity Profiling ICCV 2025 MonoDVPS: A Self-Supervised Monocular Depth Estimation Approach to Depth-Aware Video Panoptic Segmentation WACV 2023 Exploiting Pseudo Labels in a Self-Supervised Learning Framework for Improved Monocular Depth Estimation CVPR 2022 Time-Space Transformers for Video Panoptic Segmentation WACV 2022 Fast Boosting Based Detection Using Scale Invariant Multimodal Multiresolution Filtered Features CVPR 2017 Semantic Channels for Fast Pedestrian Detection CVPR 2016 Word Channel Based Multiscale Pedestrian Detection Without Image Resizing and Using Only One Classifier CVPR 2014