Karteek Alahari

34 papers · 2013–2025 · 9 conferences · across top CS/AI conferences

Achievements

+13 more ↓

🏃 Academic Marathon (12) 🌍 Conference Polyglot (9) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (7)

🧭 Keyword Pioneer 🐝 Cross-Pollinator (7) 🌍 Conference Polyglot (9) 🤝 Dynamic Duo (13) 🌱 Topic Pioneer 🧬 Topic Evolution 🗃️ Keyword Collector (126) 🚀 Conference Pioneer 📈 Trend Setter ❓ The Questioner ⚡ Prolific Year (5) 🔥 Unstoppable (9) 💎 Century Club (34)

Conferences

CVPR (9) ICCV (9) ECCV (4) ICLR (3) NIPS (3) CORL (2) WACV (2) ICML (1) INTERSPEECH (1)

Top co-authors

Cordelia Schmid (13) Jakob Verbeek (6) Yannis Kalantidis (3) Pietro Astolfi (3) Enrico Fini (3) Elisa Ricci (3) Konstantin Shmelkov (3) Valentin Gabeur (3) Tariq Berrada (3) Julien Mairal (3)

Research topics

Computer Vision (1) Domain-Specific (1)

Keywords

self-supervised learning (5) transfer learning (3) semi-supervised learning (3) representation learning (3) semantic segmentation (3) knowledge distillation (3) image classification (3) generative adversarial network (2) continual learning (2) image generation (2) action recognition (2) optical flow (2) depth estimation (2) object detection (2) human pose estimation (2) variational autoencoder (2) image restoration (1) variational inference (1) nonconvex optimization (1) benchmark evaluation (1)

Papers

Boosting Latent Diffusion with Perceptual Objectives ICLR 2025 Advancing Prompt-Based Methods for Replay-Independent General Continual Learning ICLR 2025 Guided Distillation for Semi-Supervised Instance Segmentation WACV 2024 On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models NIPS 2024 Unlocking Pre-trained Image Backbones for Semantic Image Synthesis CVPR 2024 Learning Representations of Satellite Images From Metadata Supervision ECCV 2024 A Soft Nearest-Neighbor Framework for Continual Semi-Supervised Learning ICCV 2023 No Reason for No Supervision: Improved Generalization in Supervised Models ICLR 2023 Semi-Supervised Learning Made Simple With Self-Supervised Clustering CVPR 2023 Fake It Till You Make It: Learning Transferable Representations From Synthetic ImageNet Clones CVPR 2023 Self-Supervised Models Are Continual Learners CVPR 2022 Masking Modalities for Cross-Modal Video Retrieval WACV 2022 Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping CORL 2022 AVATAR: Unconstrained Audiovisual Speech Recognition INTERSPEECH 2022 LaRa: Latents and Rays for Multi-Camera Bird’s-Eye-View Semantic Segmentation CORL 2022 Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond NIPS 2021 Concept Generalization in Visual Representation Learning ICCV 2021 Meta-Learning with Shared Amortized Variational Inference ICML 2020 Multi-modal Transformer for Video Retrieval ECCV 2020 Adaptive Density Estimation for Generative Models NIPS 2019 MARS: Motion-Augmented RGB Stream for Action Recognition CVPR 2019 How good is my GAN? ECCV 2018 Actor and Observer: Joint Modeling of First and Third-Person Videos CVPR 2018 End-to-End Incremental Learning ECCV 2018 Learning Video Object Segmentation With Visual Memory ICCV 2017 Learning Motion Patterns in Videos CVPR 2017 Incremental Learning of Object Detectors Without Catastrophic Forgetting ICCV 2017 Online Object Tracking With Proposal Selection ICCV 2015 Mixing Body-Part Sequences for Human Pose Estimation CVPR 2014 Learning to Estimate and Remove Non-uniform Image Blur CVPR 2013 Image Retrieval Using Textual Cues ICCV 2013 Pose Estimation and Segmentation of People in 3D Movies ICCV 2013 Learning Graphs to Match ICCV 2013 Decomposing Bag of Words Histograms ICCV 2013