Picture for Toby Perrett

Toby Perrett

Spatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind

Add code
Apr 07, 2024
Viaarxiv icon

Centre Stage: Centricity-based Audio-Visual Temporal Action Detection

Add code
Nov 28, 2023
Figure 1 for Centre Stage: Centricity-based Audio-Visual Temporal Action Detection
Figure 2 for Centre Stage: Centricity-based Audio-Visual Temporal Action Detection
Figure 3 for Centre Stage: Centricity-based Audio-Visual Temporal Action Detection
Figure 4 for Centre Stage: Centricity-based Audio-Visual Temporal Action Detection
Viaarxiv icon

What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations

Add code
Jun 14, 2023
Figure 1 for What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations
Figure 2 for What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations
Figure 3 for What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations
Figure 4 for What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations
Viaarxiv icon

Use Your Head: Improving Long-Tail Video Recognition

Add code
Apr 03, 2023
Figure 1 for Use Your Head: Improving Long-Tail Video Recognition
Figure 2 for Use Your Head: Improving Long-Tail Video Recognition
Figure 3 for Use Your Head: Improving Long-Tail Video Recognition
Figure 4 for Use Your Head: Improving Long-Tail Video Recognition
Viaarxiv icon

Refining Action Boundaries for One-stage Detection

Add code
Oct 25, 2022
Figure 1 for Refining Action Boundaries for One-stage Detection
Figure 2 for Refining Action Boundaries for One-stage Detection
Figure 3 for Refining Action Boundaries for One-stage Detection
Figure 4 for Refining Action Boundaries for One-stage Detection
Viaarxiv icon

Inertial Hallucinations -- When Wearable Inertial Devices Start Seeing Things

Add code
Jul 14, 2022
Figure 1 for Inertial Hallucinations -- When Wearable Inertial Devices Start Seeing Things
Figure 2 for Inertial Hallucinations -- When Wearable Inertial Devices Start Seeing Things
Figure 3 for Inertial Hallucinations -- When Wearable Inertial Devices Start Seeing Things
Figure 4 for Inertial Hallucinations -- When Wearable Inertial Devices Start Seeing Things
Viaarxiv icon

An Evaluation of OCR on Egocentric Data

Add code
Jun 11, 2022
Figure 1 for An Evaluation of OCR on Egocentric Data
Figure 2 for An Evaluation of OCR on Egocentric Data
Figure 3 for An Evaluation of OCR on Egocentric Data
Figure 4 for An Evaluation of OCR on Egocentric Data
Viaarxiv icon

TVNet: Temporal Voting Network for Action Localization

Add code
Jan 02, 2022
Figure 1 for TVNet: Temporal Voting Network for Action Localization
Figure 2 for TVNet: Temporal Voting Network for Action Localization
Figure 3 for TVNet: Temporal Voting Network for Action Localization
Figure 4 for TVNet: Temporal Voting Network for Action Localization
Viaarxiv icon

Temporal-Relational CrossTransformers for Few-Shot Action Recognition

Add code
Jan 15, 2021
Figure 1 for Temporal-Relational CrossTransformers for Few-Shot Action Recognition
Figure 2 for Temporal-Relational CrossTransformers for Few-Shot Action Recognition
Figure 3 for Temporal-Relational CrossTransformers for Few-Shot Action Recognition
Figure 4 for Temporal-Relational CrossTransformers for Few-Shot Action Recognition
Viaarxiv icon

Meta-Learning with Context-Agnostic Initialisations

Add code
Jul 29, 2020
Figure 1 for Meta-Learning with Context-Agnostic Initialisations
Figure 2 for Meta-Learning with Context-Agnostic Initialisations
Figure 3 for Meta-Learning with Context-Agnostic Initialisations
Figure 4 for Meta-Learning with Context-Agnostic Initialisations
Viaarxiv icon