Fine-tuning visual models has been widely shown promising performance on many
downstream visual tasks. With the surprising development of pre-trained visual foundation …

As the model size of pre-trained language models (PLMs) grows rapidly, full fine-tuning
becomes prohibitively expensive for model training and storage. In vision-and-language …

Vision-and-language pretraining (VLP) models have experienced a surge in popularity
recently. By fine-tuning them on specific datasets, significant performance improvements …

Text-video retrieval is an important multi-modal learning task, where the goal is to retrieve
the most relevant video for a given text query. Recently, pre-trained models, eg, CLIP, show …

Recently, vision transformer (ViT) based multimodal learning methods have been proposed
to improve the robustness of face anti-spoofing (FAS) systems. However, there are still no …

Short-form UGC video platforms like Kwai and TikTok have been an emerging and
irreplaceable mainstream media form thriving on user-friendly engagement and …

Recently temporal action detection (TAD) has seen significant performance improvement
with end-to-end training. However due to the memory bottleneck only models with limited …

The visual models pretrained on large-scale benchmarks encode general knowledge and
prove effective in building more powerful representations for downstream tasks. Most …

Natural image compression has been greatly improved in the deep learning era. However,
the compression performance will be heavily degraded if the pretrained encoder is directly …

The limited availability of labelled data in Action Quality Assessment (AQA), has forced
previous works to fine-tune their models pretrained on large-scale domain-general datasets …