Anelia Angelova

papers

1,444

total citations

papers (20)

Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers

CVPR 2023arXiv

113

citations

SMURF: Self-Teaching Multi-Frame Unsupervised RAFT With Full-Image Warping

CVPR 2021arXiv

106

citations

Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve

ECCV 2020arXiv

citations

Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning

CVPR 2023arXiv

citations

4D-Net for Learned Multi-Modal Alignment

ICCV 2021arXiv

citations

AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification

ECCV 2020arXiv

citations

Contrastive Feature Masking Open-Vocabulary Vision Transformer

ICCV 2023arXiv

citations

Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval From a Single Image

ICCV 2021arXiv

citations

Adversarial Generative Grammars for Human Activity Prediction

ECCV 2020arXiv

citations

Taskology: Utilizing Task Relations at Scale

CVPR 2021arXiv

citations

Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities

CVPR 2024arXiv

citations

Video Question Answering with Iterative Video-Text Co-Tokenization

ECCV 2022arXiv

citations

FindIt: Generalized Localization with Natural Language Queries

ECCV 2022arXiv

citations

VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models

CVPR 2025arXiv

citations

AssembleNet++: Assembling Modality Representations via Attention Connections - Supplementary Material -

ECCV 2020

citations

TokenLearner: Adaptive Space-Time Tokenization for Videos

NEURIPS 2021

citations

Anelia Angelova

papers (20)

On Scaling Up a Multilingual Vision and Language Model

What Matters in Unsupervised Optical Flow

Evolving Losses for Unsupervised Video Representation Learning

KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects

Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers

SMURF: Self-Teaching Multi-Frame Unsupervised RAFT With Full-Image Warping

Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve

Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning

4D-Net for Learned Multi-Modal Alignment

AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification

Contrastive Feature Masking Open-Vocabulary Vision Transformer

Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval From a Single Image

Adversarial Generative Grammars for Human Activity Prediction

Taskology: Utilizing Task Relations at Scale

Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities

Video Question Answering with Iterative Video-Text Co-Tokenization

FindIt: Generalized Localization with Natural Language Queries

VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models

AssembleNet++: Assembling Modality Representations via Attention Connections - Supplementary Material -

TokenLearner: Adaptive Space-Time Tokenization for Videos

papers (20)

On Scaling Up a Multilingual Vision and Language Model

What Matters in Unsupervised Optical Flow

Evolving Losses for Unsupervised Video Representation Learning

KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects

Region-Aware Pretraining for Open-Vocabulary Object Detection With Vision Transformers

SMURF: Self-Teaching Multi-Frame Unsupervised RAFT With Full-Image Warping

Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve

Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning

4D-Net for Learned Multi-Modal Alignment

AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification

Contrastive Feature Masking Open-Vocabulary Vision Transformer

Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval From a Single Image

Adversarial Generative Grammars for Human Activity Prediction

Taskology: Utilizing Task Relations at Scale

Mirasol3B: A Multimodal Autoregressive Model for Time-Aligned and Contextual Modalities

Video Question Answering with Iterative Video-Text Co-Tokenization

FindIt: Generalized Localization with Natural Language Queries

VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models

AssembleNet++: Assembling Modality Representations via Attention Connections - Supplementary Material -

TokenLearner: Adaptive Space-Time Tokenization for Videos