Search Results - "Albanie, Samuel"

Squeeze-and-Excitation Networks by Hu, Jie, Shen, Li, Albanie, Samuel, Sun, Gang, Wu, Enhua

“…The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by…”
Get full text

Seeing Voices and Hearing Faces: Cross-Modal Biometric Matching by Nagrani, Arsha, Albanie, Samuel, Zisserman, Andrew

“…We introduce a seemingly impossible task: given only an audio clip of someone speaking, decide which of two face images is the speaker. In this paper we study…”
Get full text

Disentangled Speech Embeddings Using Cross-Modal Self-Supervision by Nagrani, Arsha, Chung, Joon Son, Albanie, Samuel, Zisserman, Andrew

“…The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised…”
Get full text

Unsupervised Learning of Landmarks by Descriptor Vector Exchange by Thewlis, James, Albanie, Samuel, Bilen, Hakan, Vedaldi, Andrea

“…Equivariance to random image transformations is an effective method to learn landmarks of object categories, such as the eyes and the nose in faces, without…”
Get full text

Adaptive Cross-Modal Prototypes for Cross-Domain Visual-Language Retrieval by Liu, Yang, Chen, Qingchao, Albanie, Samuel

“…In this paper, we study the task of visual-text retrieval in the highly practical setting in which labelled visual data with paired text descriptions are…”
Get full text

All you need are a few pixels: semantic segmentation with PixelPick by Shin, Gyungin, Xie, Weidi, Albanie, Samuel

“…A central challenge for the task of semantic segmentation is the prohibitive cost of obtaining dense pixel-level annotations to supervise model training. In…”
Get full text

TeachText: CrossModal text-video retrieval through generalized distillation by Croitoru, Ioana, Bogolin, Simion-Vlad, Leordeanu, Marius, Jin, Hailin, Zisserman, Andrew, Liu, Yang, Albanie, Samuel

“…In recent years, considerable progress on the task of text-video retrieval has been achieved by leveraging large-scale pretraining on visual and audio datasets…”
Get full text

Scaling Up Sign Spotting Through Sign Language Dictionaries by Varol, Gül, Momeni, Liliane, Albanie, Samuel, Afouras, Triantafyllos, Zisserman, Andrew

“…The focus of this work is sign spotting –given a video of an isolated sign, our task is to identify whether and where it has been signed in a continuous,…”
Get full text

Self-Supervised Learning of Geometrically Stable Features Through Probabilistic Introspection by Novotny, David, Albanie, Samuel, Larlus, Diane, Vedaldi, Andrea

“…Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks. While self-supervision has usually been…”
Get full text

TeachText: CrossModal Generalized Distillation for Text-Video Retrieval by Croitoru, Ioana, Bogolin, Simion-Vlad, Leordeanu, Marius, Jin, Hailin, Zisserman, Andrew, Albanie, Samuel, Liu, Yang

“…In recent years, considerable progress on the task of text-video retrieval has been achieved by leveraging large-scale pretraining on visual and audio datasets…”
Get full text

Cross Modal Retrieval with Querybank Normalisation by Bogolin, Simion-Vlad, Croitoru, Ioana, Jin, Hailin, Liu, Yang, Albanie, Samuel

“…Profiting from large-scale training datasets, advances in neural architecture design and efficient inference, joint embeddings have become the dominant…”
Get full text

Movement change detected by optical flow precedes, but does not predict, tail-biting in pigs by Larsen, Mona Lilian Vestbjerg, Pedersen, Lene Juul, Edwards, Sandra, Albanie, Samuel, Dawkins, Marian Stamp

“…•Optical flow was used to monitor pig movement before an outbreak of tail-biting.•There was increased group movement in the three days prior to…”
Get full text

Read and Attend: Temporal Localisation in Sign Language Videos by Varol, Gul, Momeni, Liliane, Albanie, Samuel, Afouras, Triantafyllos, Zisserman, Andrew

“…The objective of this work is to annotate sign instances across a broad vocabulary in continuous sign language. We train a Transformer model to ingest a…”
Get full text

Sign Language Video Retrieval with Free-Form Textual Queries by Duarte, Amanda, Albanie, Samuel, Giro-I-Nieto, Xavier, Varol, Gul

“…Systems that can efficiently search collections of sign language videos have been highlighted as a useful application of sign language technology. However, the…”
Get full text

Audio Retrieval With Natural Language Queries: A Benchmark Study by Koepke, A. Sophia, Oncescu, Andreea-Maria, Henriques, Joao F., Akata, Zeynep, Albanie, Samuel

“…The objectives of this work are cross-modal text-audio and audio-text retrieval , in which the goal is to retrieve the audio content from a pool of candidates…”
Get full text

Unsupervised Salient Object Detection with Spectral Cluster Voting by Shin, Gyungin, Albanie, Samuel, Xie, Weidi

“…In this paper, we tackle the challenging task of unsupervised salient object detection (SOD) by leveraging spectral clustering on self-supervised features. We…”
Get full text

A Sound Approach: Using Large Language Models to Generate Audio Descriptions for Egocentric Text-Audio Retrieval by Oncescu, Andreea-Maria, Henriques, Joao F., Zisserman, Andrew, Albanie, Samuel, Koepke, A. Sophia

“…Video databases from the internet are a valuable source of text-audio retrieval datasets. However, given that sound and vision streams represent different…”
Get full text

Sign Language Segmentation with Temporal Convolutional Networks by Renz, Katrin, Stache, Nicolaj C., Albanie, Samuel, Varol, Gul

“…The objective of this work is to determine the location of temporal boundaries between signs in continuous sign language videos. Our approach employs 3D…”
Get full text

Aligning Subtitles in Sign Language Videos by Bull, Hannah, Afouras, Triantafyllos, Varol, Gul, Albanie, Samuel, Momeni, Liliane, Zisserman, Andrew

“…The goal of this work is to temporally align asynchronous subtitles in sign language videos. In particular, we focus on sign-language interpreted TV broadcast…”
Get full text

QUERYD: A Video Dataset with High-Quality Text and Audio Narrations by Oncescu, Andreea-Maria, Henriques, Joao F., Liu, Yang, Zisserman, Andrew, Albanie, Samuel

“…We introduce QuerYD, a new large-scale dataset for retrieval and event localisation in video. A unique feature of our dataset is the availability of two audio…”
Get full text