Existing text-video retrieval solutions are, in essence, discriminant models focused on
maximizing the conditional likelihood, ie, p (candidates| query). While straightforward, this …

Most text-driven human motion generation methods employ sequential modeling
approaches, eg, transformer, to extract sentence-level text representations automatically and …

With the explosive growth of web videos and emerging large-scale vision-language pre-
training models, eg, CLIP, retrieving videos of interest with text instructions has attracted …

Image Retrieval aims to retrieve corresponding images based on a given query. In
application scenarios, users intend to express their retrieval intent through various query …

Abstract Open-world Semi-Supervised Learning (OSSL) is a realistic and challenging task,
aiming to classify unlabeled samples from both seen and novel classes using partially …

Multimodal representation learning, with contrastive learning, plays an important role in the
artificial intelligence domain. As an important subfield, video-language representation …

Video Question Answering (VideoQA) aims to answer natural language questions based on
the information observed in videos. Despite the recent success of Large Multimodal Models …

Previous audio-text retrieval (ATR) methods primarily concentrate on constructing
contrastive pairs between entire audio clips and full caption sentences, while neglecting fine …

Text-based Visual Question Answering~(TextVQA) aims to produce correct answers for
given questions about the images with multiple scene texts. In most cases, the texts naturally …

Applying CNN on embedded systems is challenging due to model size limitations. Pruning
and quantization can help, but are time-consuming to apply separately. Our Single-Shot …