Open-vocabulary video anomaly detection
Current video anomaly detection (VAD) approaches with weak supervisions are inherently
limited to a closed-set setting and may struggle in open-world applications where there can …
limited to a closed-set setting and may struggle in open-world applications where there can …
Open-vocabulary semantic segmentation via attribute decomposition-aggregation
Open-vocabulary semantic segmentation is a challenging task that requires segmenting
novel object categories at inference time. Recent works explore vision-language pre-training …
novel object categories at inference time. Recent works explore vision-language pre-training …
Distilling vision-language pre-training to collaborate with weakly-supervised temporal action localization
Weakly-supervised temporal action localization (WTAL) learns to detect and classify action
instances with only category labels. Most methods widely adopt the off-the-shelf …
instances with only category labels. Most methods widely adopt the off-the-shelf …
Audio-Visual Segmentation via Unlabeled Frame Exploitation
Audio-visual segmentation (AVS) aims to segment the sounding objects in video frames.
Although great progress has been witnessed we experimentally reveal that current methods …
Although great progress has been witnessed we experimentally reveal that current methods …
Multi-modal prototypes for open-set semantic segmentation
In semantic segmentation, adapting a visual system to novel object categories at inference
time has always been both valuable and challenging. To enable such generalization …
time has always been both valuable and challenging. To enable such generalization …
Turbo: Informativity-driven acceleration plug-in for vision-language models
Vision-Language Large Models (VLMs) have become primary backbone of AI, due to the
impressive performance. However, their expensive computation costs, ie, throughput and …
impressive performance. However, their expensive computation costs, ie, throughput and …
Com-stal: Compositional spatio-temporal action localization
Spatio-temporal action localization aims to locate the spatial and temporal positions of
actors and classify their actions. However, prior research overlooks the fact that human …
actors and classify their actions. However, prior research overlooks the fact that human …
Zero-Shot Temporal Action Detection by Learning Multimodal Prompts and Text-Enhanced Actionness
Zero-shot temporal action detection (ZS-TAD), aiming to recognize and detect new and
unseen video actions, is an emerging and challenging task with limited solutions. Recent …
unseen video actions, is an emerging and challenging task with limited solutions. Recent …
Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models
C Ju, H Wang, H Cheng, X Chen, Z Zhai… - arXiv preprint arXiv …, 2024 - arxiv.org
Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the
impressive performance. However, their expensive computation costs, ie, throughput and …
impressive performance. However, their expensive computation costs, ie, throughput and …
AttrSeg: open-vocabulary semantic segmentation via attribute decomposition-aggregation
C Ma, Y Yang, C Ju, F Zhang, Y Zhang… - … -seventh Conference on …, 2023 - openreview.net
Open-vocabulary semantic segmentation is a challenging task that requires segmenting
novel object categories at inference time. Recent works explore vision-language pre-training …
novel object categories at inference time. Recent works explore vision-language pre-training …