Search Results for author:
Found 7 papers, 1 papers with code
Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis
These challenges encompass maintaining the content consistency between the input video and the generated audio, as well as the alignment of temporal and loudness properties within the video.
Defying Imbalanced Forgetting in Class Incremental Learning
This intriguing phenomenon, discovered in replay-based Class Incremental Learning (CIL), highlights the imbalanced forgetting of learned classes, as their accuracy is similar before the occurrence of catastrophic forgetting.
Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation
For the first time, our framework explores three types of bilateral entanglements within AVS: pixel entanglement, modality entanglement, and temporal entanglement.
Bilateral Memory Consolidation for Continual Learning
Humans are proficient at continuously acquiring and integrating new knowledge.
Pro-tuning: Unified Prompt Tuning for Vision Tasks
To this end, we propose parameter-efficient Prompt tuning (Pro-tuning) to adapt frozen vision models to various downstream vision tasks.
AME: Attention and Memory Enhancement in Hyper-Parameter Optimization
Training Deep Neural Networks (DNNs) is inherently subject to sensitive hyper-parameters and untimely feedbacks of performance evaluation.
Differentiable Convolution Search for Point Cloud Processing
It can work in a purely data-driven manner and thus is capable of auto-creating a group of suitable convolutions for geometric shape modeling.
