Continual Text-to-Video Retrieval with Frame Fusion and Task-Aware Routing
Open Access
- 13 July 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1011-1021
Abstract
No abstract availableAll Related Versions
Funding Information
- Australian Research Council (DP240101814,DE230101033,LP230200892,CE200100025)
This publication has 37 references indexed in Scilit:
- CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval and captioningNeurocomputing, 2022
- X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval2022
- Learning to Prompt for Continual Learning2022
- Robust fine-tuning of zero-shot models2022
- Memory Aware Synapses: Learning What (not) to Forget2018
- A Joint Sequence Fusion Model for Video Question Answering and Retrieval2018
- iCaRL: Incremental Classifier and Representation Learning2017
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- MSR-VTT: A Large Video Description Dataset for Bridging Video and Language2016
- ActivityNet: A large-scale video benchmark for human activity understanding2015