Arsha Nagrani
42 papers · 2017–2026 · 8 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 ↓+10 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (65) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π₯
Mega-Team Β· Squad
π
Keyword Champion
(5)
π€
Dynamic Duo
(22)
π¬
Deep Specialist
(19)
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Silver
β
The Questioner
π
Century Club Β· Bronze
π
Conference Pioneer
ποΈ
Keyword Collector
(171)
Top co-authors
Research topics
Computer Vision
(24)
Artificial Intelligence
(23)
Core AI
(22)
Deep Learning
(20)
Learning Types Β· Deep Learning
(19)
Machine Learning
(17)
Natural Language Processing
(14)
Processing
(14)
Learning Types Β· Machine Learning
(13)
Generation Β· Computer Vision
(7)
Generation Β· Natural Language Processing
(7)
Analysis
(6)
Speech & Audio
(5)
Architectures
(5)
Core Methods
(5)
Keywords
multimodal learning
(15)
video understanding
(13)
video-language model
(5)
video captioning
(5)
vision-language model
(5)
large language model
(4)
contrastive learning
(4)
visual question answering
(4)
temporal localization
(4)
audio description
(3)
speaker verification
(3)
cross-modal learning
(3)
self-supervised learning
(3)
automatic speech recognition
(3)
video question answering
(3)
video reasoning
(3)
dense video captioning
(3)
transformer architecture
(2)
efficient computing
(2)
zero-shot learning
(2)
Papers
CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning
CVPR 2026
CURVE: A Benchmark for Cultural and Multilingual Long Video Reasoning
CVPR 2026
Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding
CVPR 2026
Flexible Frame Selection for Efficient Video Reasoning
CVPR 2025
MINERVA: Evaluating Complex Video Reasoning
ICCV 2025
Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation
ICCV 2025
Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks
CVPR 2025
AutoAD III: The Prequel - Back to the Pixels
CVPR 2024
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
NeurIPS 2024
MoReVQA: Exploring Modular Reasoning Models for Video Question Answering
CVPR 2024
On Scaling Up a Multilingual Vision and Language Model
CVPR 2024
Streaming Dense Video Captioning
CVPR 2024
VicTR: Video-conditioned Text Representations for Activity Recognition
CVPR 2024
VIEWS: Entity-Aware News Video Captioning
EMNLP 2024
AutoAD II: The Sequel - Who, When, and What in Movie Audio Description
ICCV 2023
AutoAD: Movie Description in Context
CVPR 2023
AVFormer: Injecting Vision Into Frozen Speech Models for Zero-Shot AV-ASR
CVPR 2023
LanSER: Language-Model Supported Speech Emotion Recognition
Interspeech 2023
Modular Visual Question Answering via Code Generation
ACL 2023
UnLoc: A Unified Framework for Video Localization Tasks
ICCV 2023
Verbs in Action: Improving Verb Understanding in Video-Language Models
ICCV 2023
Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
CVPR 2023
VidChapters-7M: Video Chapters at Scale
NeurIPS 2023
AVATAR: Unconstrained Audiovisual Speech Recognition
Interspeech 2022
End-to-End Generative Pretraining for Multimodal Video Captioning
CVPR 2022
Learning Audio-Video Modalities from Image Captions
ECCV 2022
Masking Modalities for Cross-Modal Video Retrieval
WACV 2022
TL;DW? Summarizing Instructional Videos with Task Relevance & Cross-Modal Saliency
ECCV 2022
Attention Bottlenecks for Multimodal Fusion
NeurIPS 2021
Composable Augmentation Encoding for Video Representation Learning
ICCV 2021
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
ICCV 2021
Localizing Visual Sounds the Hard Way
CVPR 2021
Look Before You Speak: Visually Contextualized Utterances
CVPR 2021
Recognizing Multimodal Entailment
ACL 2021
Speech2Action: Cross-Modal Supervision for Action Recognition
CVPR 2020
Spot the Conversation: Speaker Diarisation in the Wild
Interspeech 2020
Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos
ECCV 2020
EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition
ICCV 2019
Learnable PINs: Cross-Modal Embeddings for Person Identity
ECCV 2018
Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching
CVPR 2018
VoxCeleb2: Deep Speaker Recognition
Interspeech 2018
VoxCeleb: A Large-Scale Speaker Identification Dataset
Interspeech 2017