Arsha Nagrani
Computer Vision and Pattern Recognition · 2017–2023
A researcher in the Science corpus: 19 papers; trusts 2,766 researchers and is trusted by 1,847 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 716 citations into it; #1,373 of 21,973 by trust here, #2,248 by citations
- Artificial Intelligence — 544 citations into it; #1,851 of 36,961 by trust here, #2,932 by citations
- Multimodal Learning — 284 citations into it; #169 of 1,215 by trust here, #239 by citations
- Signal Processing — 185 citations into it; #137 of 7,592 by trust here, #239 by citations
- Evaluation & Benchmarks — 120 citations into it; #486 of 3,155 by trust here, #1,193 by citations
- Representation & Self-Supervised Learning — 118 citations into it
- Natural Language Processing — 109 citations into it
- Model Architectures — 67 citations into it
Whom Arsha Nagrani trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Andrew Zisserman
- Karen Simonyan
- Geoffrey E. Hinton
- Kaiming He
- Alex Krizhevsky
- Diederik P. Kingma
- Sergey Ioffe
- Yoshua Bengio
- Yann LeCun
- Ross B. Girshick
Who trusts Arsha Nagrani overall
- Joon Son Chung
- Andrew Zisserman
- Samuel Albanie
- Olivia Wiles
- Andrea Vedaldi
- Kristen Grauman
- Ruohan Gao
- Mirco Ravanelli
- Weidi Xie
- Yoshua Bengio
Papers from Arsha Nagrani's perspective
Ordered by how strongly the researchers Arsha Nagrani trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- ImageNet Large Scale Visual Recognition Challenge
- Going deeper with convolutions
Their papers
- Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval (2021) — 1,620 citations
- Use What You Have: Video retrieval using representations from collaborative experts (2019) — 445 citations
- EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition (2019) — 403 citations
- VoxCeleb: A Large-Scale Speaker Identification Dataset (2017) — 2,732 citations
- VoxCeleb2: Deep Speaker Recognition (2018) — 2,807 citations
- Attention Bottlenecks for Multimodal Fusion (2021) — 825 citations
- End-to-end Generative Pretraining for Multimodal Video Captioning (2022) — 201 citations
- Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching (2018) — 253 citations
- PaLI-X: On Scaling up a Multilingual Vision and Language Model (2023) — 301 citations
- Look Before you Speak: Visually Contextualized Utterances (2020) — 71 citations
- Speech2Action: Cross-Modal Supervision for Action Recognition (2020) — 62 citations
- Emotion Recognition in Speech using Cross-Modal Transfer in the Wild (2018) — 291 citations
- Learnable PINs: Cross-Modal Embeddings for Person Identity (2018) — 169 citations
- Voxceleb: Large-scale speaker verification in the wild (2020) — 848 citations
- Condensed Movies: Story Based Retrieval with Contextual Embeddings (2020) — 127 citations
- Utterance-level Aggregation for Speaker Recognition in the Wild (2019) — 370 citations
- Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning (2023) — 401 citations
- Modular Visual Question Answering via Code Generation (2023) — 68 citations
- Spot the conversation: speaker diarisation in the wild (2020) — 198 citations