Deva Ramanan

Using Diffusion Priors for Video Amodal Segmentation CVPR 2025 Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features ICCV 2025 Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization ICCV 2025 Neural Eulerian Scene Flow Fields ICLR 2025 InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning ACL 2025 Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models ICLR 2025 AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis CVPR 2025 MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion ICCV 2025 ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models ICCV 2025 Towards Foundational Models for Single-Chip Radar ICCV 2025 DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion CVPR 2025 Reanimating Images using Neural Representations of Dynamic Stimuli CVPR 2025 Generating Physically Stable and Buildable Brick Structures from Text ICCV 2025 Revisiting Few-Shot Object Detection with Vision-Language Models NIPS 2024 HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces CVPR 2024 Language Models as Black-Box Optimizers for Vision-Language Models CVPR 2024 SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM CVPR 2024 The Neglected Tails in Vision-Language Models CVPR 2024 Re-Evaluating LiDAR Scene Flow WACV 2024 NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples NIPS 2024 Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection CORL 2024 ZeroFlow: Scalable Scene Flow via Distillation ICLR 2024 Cameras as Rays: Pose Estimation via Ray Diffusion ICLR 2024 Better Call SAL: Towards Learning to Segment Anything in Lidar ECCV 2024 FlashTex: Fast Relightable Mesh Texturing with LightControlNet ECCV 2024 I Can't Believe It's Not Scene Flow! ECCV 2024 Evaluating Text-to-Visual Generation with Image-to-Text Generation ECCV 2024 Revisiting the Role of Language Priors in Vision-Language Models ICML 2024 Joint Metrics Matter: A Better Standard for Trajectory Forecasting ICCV 2023 Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting CVPR 2023 Learning To Zoom and Unzoom CVPR 2023 Soft Augmentation for Image Classification CVPR 2023 TarViS: A Unified Approach for Target-Based Video Segmentation CVPR 2023 Far3Det: Towards Far-Field 3D Detection WACV 2023 BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video WACV 2023 Pix2map: Cross-Modal Retrieval for Inferring Street Maps From Images CVPR 2023 Learning Lightweight Object Detectors via Multi-Teacher Progressive Distillation ICML 2023 SUDS: Scalable Urban Dynamic Scenes CVPR 2023 Reconstructing Animatable Categories From Videos CVPR 2023 Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning With Multimodal Models CVPR 2023 Distilling Neural Fields for Real-Time Articulated Shape Reconstruction CVPR 2023 3D-Aware Conditional Image Synthesis CVPR 2023 PyNeRF: Pyramidal Neural Radiance Fields NIPS 2023 PPR: Physically Plausible Reconstruction from Monocular Videos ICCV 2023 Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesis ICCV 2023 Depth-Supervised NeRF: Fewer Views and Faster Training for Free CVPR 2022 Differentiable Raycasting for Self-Supervised Occupancy Forecasting ECCV 2022 RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild ECCV 2022 Multimodal Object Detection via Probabilistic Ensembling ECCV 2022 Learning to Discover and Detect Objects NIPS 2022 Continual Learning with Evolving Class Ontologies NIPS 2022 HODOR: High-Level Object Descriptors for Object Re-Segmentation in Video Learned From Static Images CVPR 2022 BANMo: Building Animatable 3D Neural Models From Many Casual Videos CVPR 2022 Mega-NERF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs CVPR 2022 Forecasting From LiDAR via Future Object Detection CVPR 2022 Towards Long-Tailed 3D Detection CORL 2022 Opening Up Open World Tracking CVPR 2022 Long-Tailed Recognition via Weight Balancing CVPR 2022 Learning Rare Category Classifiers on a Tight Labeling Budget ICCV 2021 ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction NIPS 2021 NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild NIPS 2021 Safe Local Motion Planning With Self-Supervised Freespace Forecasting CVPR 2021 Background Splitting: Finding Rare Classes in a Sea of Background CVPR 2021 LASR: Learning Articulated Shape Reconstruction From a Monocular Video CVPR 2021 Learning To Segment Rigid Motions From Two Frames CVPR 2021 FOVEA: Foveated Image Magnification for Autonomous Navigation ICCV 2021 OpenGAN: Open-Set Recognition via Open Data Generation ICCV 2021 Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories ICCV 2021 Detecting Invisible People ICCV 2021 Do Image Classifiers Generalize Across Time? ICCV 2021 Unsupervised Audiovisual Synthesis via Exemplar Autoencoders ICLR 2021 What You See is What You Get: Exploiting Visibility for 3D Object Detection CVPR 2020 CATER: A diagnostic dataset for Compositional Actions & TEmporal Reasoning ICLR 2020 Towards Streaming Perception ECCV 2020 Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints ICLR 2020 MetaPix: Few-Shot Video Retargeting ICLR 2020 Learning to Move with Affordance Maps ICLR 2020 Upgrading Optical Flow to 3D Scene Flow Through Optical Expansion CVPR 2020 Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild ECCV 2020 TAO: A Large-Scale Benchmark for Tracking Any Object ECCV 2020 4D Visualization of Dynamic Events From Unconstrained Multi-View Videos CVPR 2020 Online Model Distillation for Efficient Video Inference ICCV 2019 Weakly-Supervised Action Localization With Background Modeling ICCV 2019 Active Learning with Partial Feedback ICLR 2019 Shapes and Context: In-The-Wild Image Synthesis & Manipulation CVPR 2019 Meta-Learning to Detect Rare Objects ICCV 2019 Volumetric Correspondence Networks for Optical Flow NIPS 2019 Argoverse: 3D Tracking and Forecasting With Rich Maps CVPR 2019 Hierarchical Deep Stereo Matching on High-Resolution Images CVPR 2019 Towards Latent Attribute Discovery From Triplet Similarities ICCV 2019 DistInit: Learning Video Representations Without a Single Labeled Video ICCV 2019 PixelNN: Example-based Image Synthesis ICLR 2018 Few-Shot Human Motion Prediction via Meta-Learning ECCV 2018 Active Testing: An Efficient and Robust Framework for Estimating Accuracy ICML 2018 Recycle-GAN: Unsupervised Video Retargeting ECCV 2018 Growing a Brain: Fine-Tuning by Increasing Model Capacity CVPR 2017 3D Human Pose Estimation = 2D Pose Estimation + Matching CVPR 2017 Expecting the Unexpected: Training Detectors for Unusual Pedestrians With Adversarial Imposters CVPR 2017 Predictive-Corrective Networks for Action Detection CVPR 2017 Learning Policies for Adaptive Tracking With Deep Feature Cascades ICCV 2017 Tracking as Online Decision-Making: Learning a Policy From Streaming Videos With Reinforcement Learning ICCV 2017 Need for Speed: A Benchmark for Higher Frame Rate Object Tracking ICCV 2017 Learning to Model the Tail NIPS 2017 ActionVLAD: Learning Spatio-Temporal Aggregation for Action Classification CVPR 2017 Finding Tiny Faces CVPR 2017 Attentional Pooling for Action Recognition NIPS 2017 Bottom-Up and Top-Down Reasoning With Hierarchical Rectified Gaussians CVPR 2016 Multi-Scale Recognition With DAG-CNNs ICCV 2015 Understanding Everyday Hands in Action From RGB-D Images ICCV 2015 First-Person Pose Recognition Using Egocentric Workspaces CVPR 2015 Look and Think Twice: Capturing Top-Down Visual Attention With Feedback Convolutional Neural Networks ICCV 2015 Depth-Based Hand Pose Estimation: Data, Methods, and Challenges ICCV 2015 Parsing Videos of Actions with Segmental Grammars CVPR 2014 Parsing Occluded People CVPR 2014 Capturing Long-tail Distributions of Object Subcategories CVPR 2014 Analysis by Synthesis: 3D Object Recognition by Object Reconstruction CVPR 2014 Exploring Weak Stabilization for Motion Feature Extraction CVPR 2013 Histograms of Sparse Codes for Object Detection CVPR 2013 Self-Paced Learning for Long-Term Tracking CVPR 2013 Analyzing 3D Objects in Cluttered Images NIPS 2012 Statistical Tests for Optimization Efficiency NIPS 2011 Video Annotation and Tracking with Active Learning NIPS 2011 Bilinear classifiers for visual recognition NIPS 2009 Learning to parse images of articulated bodies NIPS 2006