相关论文: State Space Prompting via Gathering and Spreading …
Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extending these capabilities to video tasks remains challenging…
Frame quality deterioration is one of the main challenges in the field of video understanding. To compensate for the information loss caused by deteriorated frames, recent approaches exploit transformer-based integration modules to obtain…
We propose an efficient framework to compress massive video-frame features before feeding them into large multimodal models, thereby mitigating the severe token explosion arising from hour-long videos. Our design leverages a bidirectional…
Semantic segmentation from RGB cameras is essential to the perception of autonomous flying vehicles. The stability of predictions through the captured videos is paramount to their reliability and, by extension, to the trustworthiness of the…
Point cloud videos capture dynamic 3D motion while reducing the effects of lighting and viewpoint variations, making them highly effective for recognizing subtle and continuous human actions. Although Selective State Space Models (SSMs)…
Nowadays, navigation and ride-sharing apps have collected numerous images with spatio-temporal data. A core technology for analyzing such images, associated with spatiotemporal information, is Traffic Scene Understanding (TSU), which aims…
Pre-trained Vision Mamba (Vim) models have demonstrated exceptional performance across various computer vision tasks in a computationally efficient manner, attributed to their unique design of selective state space models. To further extend…
The framework of dominant learned video compression methods is usually composed of motion prediction modules as well as motion vector and residual image compression modules, suffering from its complex structure and error propagation…
Temporal modeling remains a fundamental challenge in video understanding, particularly as sequence lengths scale. Traditional video models relying on dense spatiotemporal attention suffer from quadratic computational costs for long videos.…
Video prediction aims to predict future frames by modeling the complex spatiotemporal dynamics in videos. However, most of the existing methods only model the temporal information and the spatial information for videos in an independent…
Although significant achievements have been achieved by recurrent neural network (RNN) based video prediction methods, their performance in datasets with high resolutions is still far from satisfactory because of the information loss…
Video semantic segmentation (VSS) plays a vital role in understanding the temporal evolution of scenes. Traditional methods often segment videos frame-by-frame or in a short temporal window, leading to limited temporal context, redundant…
Robotic motor control necessitates the ability to predict the dynamics of environments and interaction objects. However, advanced self-supervised pre-trained visual representations in robotic motor control, leveraging large-scale egocentric…
Prompt learning methods have significantly extended the transferability of pre-trained Vision-Language Models (VLMs) like CLIP for various downstream tasks. These methods adopt handcraft templates or learnable vectors to provide text or…
This paper proposes a novel pretext task to address the self-supervised video representation learning problem. Specifically, given an unlabeled video clip, we compute a series of spatio-temporal statistical summaries, such as the spatial…
Video-language alignment is a crucial multi-modal task that benefits various downstream applications, e.g., video-text retrieval and video question answering. Existing methods either utilize multi-modal information in video-text pairs or…
Consecutive frames in a video contain redundancy, but they may also contain relevant complementary information for the detection task. The objective of our work is to leverage this complementary information to improve detection. Therefore,…
Existing methods for instance segmentation in videos typically involve multi-stage pipelines that follow the tracking-by-detection paradigm and model a video clip as a sequence of images. Multiple networks are used to detect objects in…
Effective modeling of complex spatiotemporal dependencies in long-form videos remains an open problem. The recently proposed Structured State-Space Sequence (S4) model with its linear complexity offers a promising direction in this space.…
Compression has been an important research topic for many decades, to produce a significant impact on data transmission and storage. Recent advances have shown a great potential of learning image and video compression. Inspired from related…