Picture for Sanjeel Parekh

Sanjeel Parekh

LTCI

Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization

Add code
May 11, 2023
Figure 1 for Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization
Figure 2 for Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization
Figure 3 for Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization
Figure 4 for Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization
Viaarxiv icon

Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF

Add code
Feb 23, 2022
Figure 1 for Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF
Figure 2 for Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF
Figure 3 for Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF
Figure 4 for Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF
Viaarxiv icon

Emotion Transfer Using Vector-Valued Infinite Task Learning

Add code
Feb 09, 2021
Figure 1 for Emotion Transfer Using Vector-Valued Infinite Task Learning
Figure 2 for Emotion Transfer Using Vector-Valued Infinite Task Learning
Figure 3 for Emotion Transfer Using Vector-Valued Infinite Task Learning
Figure 4 for Emotion Transfer Using Vector-Valued Infinite Task Learning
Viaarxiv icon

Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision

Add code
Nov 09, 2018
Figure 1 for Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision
Figure 2 for Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision
Figure 3 for Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision
Figure 4 for Identify, locate and separate: Audio-visual object extraction in large video collections using weak supervision
Viaarxiv icon

Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events

Add code
Jul 09, 2018
Figure 1 for Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events
Figure 2 for Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events
Figure 3 for Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events
Figure 4 for Weakly Supervised Representation Learning for Unsynchronized Audio-Visual Events
Viaarxiv icon

Content-based Video Indexing and Retrieval Using Corr-LDA

Add code
Feb 27, 2016
Figure 1 for Content-based Video Indexing and Retrieval Using Corr-LDA
Figure 2 for Content-based Video Indexing and Retrieval Using Corr-LDA
Figure 3 for Content-based Video Indexing and Retrieval Using Corr-LDA
Figure 4 for Content-based Video Indexing and Retrieval Using Corr-LDA
Viaarxiv icon