Arsha Nagrani

is this you? claim profile

∙ 0 followers
Google ∙ University of Oxford

DPhil Candidate at University of Oxford

Localizing Visual Sounds the Hard Way

The objective of this work is to localize sound sources that are visible...
04/06/2021 ∙ by Honglie Chen, et al. ∙ 7 ∙ share

read it
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval

Our objective in this work is video-text retrieval - in particular a joi...
04/01/2021 ∙ by Max Bain, et al. ∙ 7 ∙ share

read it
Composable Augmentation Encoding for Video Representation Learning

We focus on contrastive methods for self-supervised video representation...
04/01/2021 ∙ by Chen Sun, et al. ∙ 12 ∙ share

read it
Slow-Fast Auditory Streams For Audio Recognition

We propose a two-stream convolutional network for audio recognition, tha...
03/05/2021 ∙ by Evangelos Kazakos, et al. ∙ 4 ∙ share

read it
WiCV 2020: The Seventh Women In Computer Vision Workshop

In this paper we present the details of Women in Computer Vision Worksho...
01/11/2021 ∙ by Hazel Doughty, et al. ∙ 2 ∙ share

read it
Look Before you Speak: Visually Contextualized Utterances

While most conversational AI systems focus on textual dialogue only, con...
12/10/2020 ∙ by Paul Hongsuck Seo, et al. ∙ 2 ∙ share

read it
Cough Against COVID: Evidence of COVID-19 Signature in Cough Sounds

Testing capacity for COVID-19 remains a challenge globally due to the la...
09/17/2020 ∙ by Piyush Bagad, et al. ∙ 0 ∙ share

read it
Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos

Despite the recent advances in video classification, progress in spatio-...
07/21/2020 ∙ by Anurag Arnab, et al. ∙ 5 ∙ share

read it
Spot the conversation: speaker diarisation in the wild

The goal of this paper is speaker diarisation of videos collected 'in th...
07/02/2020 ∙ by Joon Son Chung, et al. ∙ 2 ∙ share

read it
Condensed Movies: Story Based Retrieval with Contextual Embeddings

Our objective in this work is the long range understanding of the narrat...
05/08/2020 ∙ by Max Bain, et al. ∙ 10 ∙ share

read it
Speech2Action: Cross-modal Supervision for Action Recognition

Is it possible to guess human action from dialogue alone? In this work w...
03/30/2020 ∙ by Arsha Nagrani, et al. ∙ 6 ∙ share

read it
Disentangled Speech Embeddings using Cross-modal Self-supervision

The objective of this paper is to learn representations of speaker ident...
02/20/2020 ∙ by Arsha Nagrani, et al. ∙ 17 ∙ share

read it
VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge

The VoxCeleb Speaker Recognition Challenge 2019 aimed to assess how well...
12/05/2019 ∙ by Joon Son Chung, et al. ∙ 5 ∙ share

read it
WiCV 2019: The Sixth Women In Computer Vision Workshop

In this paper we present the Women in Computer Vision Workshop - WiCV 20...
09/23/2019 ∙ by Irene Amerini, et al. ∙ 8 ∙ share

read it
Count, Crop and Recognise: Fine-Grained Recognition in the Wild

The goal of this paper is to label all the animal individuals present in...
09/19/2019 ∙ by Max Bain, et al. ∙ 34 ∙ share

read it
EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition

We focus on multi-modal fusion for egocentric action recognition, and pr...
08/22/2019 ∙ by Evangelos Kazakos, et al. ∙ 12 ∙ share

read it
Use What You Have: Video Retrieval Using Representations From Collaborative Experts

The rapid growth of video on the internet has made searching for video c...
07/31/2019 ∙ by Yang Liu, et al. ∙ 3 ∙ share

read it
Utterance-level Aggregation For Speaker Recognition In The Wild

The objective of this paper is speaker recognition "in the wild"-where u...
02/26/2019 ∙ by Weidi Xie, et al. ∙ 2 ∙ share

read it
Emotion Recognition in Speech using Cross-Modal Transfer in the Wild

Obtaining large, human labelled speech datasets to train models for emot...
08/16/2018 ∙ by Samuel Albanie, et al. ∙ 8 ∙ share

read it
VoxCeleb2: Deep Speaker Recognition

The objective of this paper is speaker recognition under noisy and uncon...
06/14/2018 ∙ by Joon Son Chung, et al. ∙ 0 ∙ share

read it
Learnable PINs: Cross-Modal Embeddings for Person Identity

We propose and investigate an identity sensitive joint embedding of face...
05/02/2018 ∙ by Arsha Nagrani, et al. ∙ 0 ∙ share

read it
Seeing Voices and Hearing Faces: Cross-modal biometric matching

We introduce a seemingly impossible task: given only an audio clip of so...
04/01/2018 ∙ by Arsha Nagrani, et al. ∙ 0 ∙ share

read it
From Benedict Cumberbatch to Sherlock Holmes: Character Identification in TV series without a Script

The goal of this paper is the automatic identification of characters in ...
01/31/2018 ∙ by Arsha Nagrani, et al. ∙ 0 ∙ share

read it
VoxCeleb: a large-scale speaker identification dataset

Most existing datasets for speaker identification contain samples obtain...
06/26/2017 ∙ by Arsha Nagrani, et al. ∙ 0 ∙ share

read it

Arsha Nagrani

Featured Co-authors

Yang Liu

Andrew Zisserman

Andrea Vedaldi

Cordelia Schmid

Chen Sun

Joon Son Chung

Rahul Sukthankar

Dima Damen

Samuel Albanie

Weidi Xie

Triantafyllos Afouras

Localizing Visual Sounds the Hard Way

Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval

Composable Augmentation Encoding for Video Representation Learning

Slow-Fast Auditory Streams For Audio Recognition

WiCV 2020: The Seventh Women In Computer Vision Workshop

Look Before you Speak: Visually Contextualized Utterances

Cough Against COVID: Evidence of COVID-19 Signature in Cough Sounds

Uncertainty-Aware Weakly Supervised Action Detection from Untrimmed Videos

Spot the conversation: speaker diarisation in the wild

Condensed Movies: Story Based Retrieval with Contextual Embeddings

Speech2Action: Cross-modal Supervision for Action Recognition

Disentangled Speech Embeddings using Cross-modal Self-supervision

VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge

WiCV 2019: The Sixth Women In Computer Vision Workshop

Count, Crop and Recognise: Fine-Grained Recognition in the Wild

EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition

Use What You Have: Video Retrieval Using Representations From Collaborative Experts

Utterance-level Aggregation For Speaker Recognition In The Wild

Emotion Recognition in Speech using Cross-Modal Transfer in the Wild

VoxCeleb2: Deep Speaker Recognition

Learnable PINs: Cross-Modal Embeddings for Person Identity

Seeing Voices and Hearing Faces: Cross-modal biometric matching

From Benedict Cumberbatch to Sherlock Holmes: Character Identification in TV series without a Script

VoxCeleb: a large-scale speaker identification dataset