Picture for Ho-Hsiang Wu

Ho-Hsiang Wu

Learning Audio Concepts from Counterfactual Natural Language

Add code
Jan 10, 2024
Viaarxiv icon

MOSAIC: Learning Unified Multi-Sensory Object Property Representations for Robot Perception

Add code
Sep 15, 2023
Viaarxiv icon

Audio-Text Models Do Not Yet Leverage Natural Language

Add code
Mar 19, 2023
Viaarxiv icon

How to Listen? Rethinking Visual Sound Localization

Add code
Apr 11, 2022
Figure 1 for How to Listen? Rethinking Visual Sound Localization
Figure 2 for How to Listen? Rethinking Visual Sound Localization
Figure 3 for How to Listen? Rethinking Visual Sound Localization
Figure 4 for How to Listen? Rethinking Visual Sound Localization
Viaarxiv icon

A Study on Robustness to Perturbations for Representations of Environmental Sound

Add code
Mar 23, 2022
Figure 1 for A Study on Robustness to Perturbations for Representations of Environmental Sound
Figure 2 for A Study on Robustness to Perturbations for Representations of Environmental Sound
Figure 3 for A Study on Robustness to Perturbations for Representations of Environmental Sound
Figure 4 for A Study on Robustness to Perturbations for Representations of Environmental Sound
Viaarxiv icon

Wav2CLIP: Learning Robust Audio Representations From CLIP

Add code
Oct 21, 2021
Figure 1 for Wav2CLIP: Learning Robust Audio Representations From CLIP
Figure 2 for Wav2CLIP: Learning Robust Audio Representations From CLIP
Figure 3 for Wav2CLIP: Learning Robust Audio Representations From CLIP
Figure 4 for Wav2CLIP: Learning Robust Audio Representations From CLIP
Viaarxiv icon

Exploring modality-agnostic representations for music classification

Add code
Jun 02, 2021
Figure 1 for Exploring modality-agnostic representations for music classification
Figure 2 for Exploring modality-agnostic representations for music classification
Figure 3 for Exploring modality-agnostic representations for music classification
Figure 4 for Exploring modality-agnostic representations for music classification
Viaarxiv icon

Multi-Task Self-Supervised Pre-Training for Music Classification

Add code
Feb 05, 2021
Figure 1 for Multi-Task Self-Supervised Pre-Training for Music Classification
Figure 2 for Multi-Task Self-Supervised Pre-Training for Music Classification
Figure 3 for Multi-Task Self-Supervised Pre-Training for Music Classification
Figure 4 for Multi-Task Self-Supervised Pre-Training for Music Classification
Viaarxiv icon

SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context

Add code
Sep 11, 2020
Figure 1 for SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context
Figure 2 for SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context
Figure 3 for SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context
Figure 4 for SONYC-UST-V2: An Urban Sound Tagging Dataset with Spatiotemporal Context
Viaarxiv icon

CodeSearchNet Challenge: Evaluating the State of Semantic Code Search

Add code
Sep 27, 2019
Figure 1 for CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
Figure 2 for CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
Figure 3 for CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
Figure 4 for CodeSearchNet Challenge: Evaluating the State of Semantic Code Search
Viaarxiv icon