Related papers: Collaborative Weakly Supervised Video Correlation …
Correspondence learning is a fundamental problem in robotics, which aims to learn a mapping between state, action pairs of agents of different dynamics or embodiments. However, current correspondence learning methods either leverage…
Continual learning (CL) aims to help deep neural networks learn new knowledge while retaining what has been learned. Owing to their powerful generalizability, pre-trained vision-language models such as Contrastive Language-Image…
Video classification is highly important with wide applications, such as video search and intelligent surveillance. Video naturally consists of static and motion information, which can be represented by frame and optical flow. Recently,…
Developing end-to-end action recognition models on long videos is fundamental and crucial for long-video action understanding. Due to the unaffordable cost of end-to-end training on the whole long videos, existing works generally train…
Vision-language models (VLMs) enable text-guided object detection but degrade severely under cross-view scenarios where ground and aerial viewpoints differ in altitude, scale, and spatial layout. These geometric changes introduce systematic…
We present Cycle-Contrastive Learning (CCL), a novel self-supervised method for learning video representation. Following a nature that there is a belong and inclusion relation of video and its frames, CCL is designed to find correspondences…
Procedure Planning in instructional videos entails generating a sequence of action steps based on visual observations of the initial and target states. Despite the rapid progress in this task, there remain several critical challenges to be…
Different from general object detection, moving infrared small target detection faces huge challenges due to tiny target size and weak background contrast.Currently, most existing methods are fully-supervised, heavily relying on a large…
The current research focus on Content-Based Video Retrieval requires higher-level video representation describing the long-range semantic dependencies of relevant incidents, events, etc. However, existing methods commonly process the frames…
Vision-Language-Action (VLA) models provide a promising paradigm for robot learning by integrating visual perception with language-guided policy learning. However, most existing approaches rely on 2D visual inputs to perform actions in 3D…
Few-shot learning (FSL) often requires effective adaptation of models using limited labeled data. However, most existing FSL methods rely on entangled representations, requiring the model to implicitly recover the unmixing process to obtain…
Inspired by the success of Self-supervised learning (SSL) in learning visual representations from unlabeled data, a few recent works have studied SSL in the context of continual learning (CL), where multiple tasks are learned sequentially,…
Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on…
Despite progress, Vision-Language-Action models (VLAs) are limited by a scarcity of large-scale, diverse robot data. While human manipulation videos offer a rich alternative, existing methods are forced to choose between small,…
Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to learn complex reasoning from long-horizon human interactions. While Multi-modal Large Language Models (MLLMs) have driven recent progress, current training…
Recent advancements in video large multimodal models (LMMs) have significantly improved their video understanding and reasoning capabilities. However, their performance drops on out-of-distribution (OOD) tasks that are underrepresented in…
With the increasing adoption of video anomaly detection in intelligent surveillance domains, conventional visual-based detection approaches often struggle with information insufficiency and high false-positive rates in complex environments.…
A fundamental aspect of compositional reasoning in a video is associating people and their actions across time. Recent years have seen great progress in general-purpose vision or video models and a move towards long-video understanding.…
Video coding, which targets to compress and reconstruct the whole frame, and feature compression, which only preserves and transmits the most critical information, stand at two ends of the scale. That is, one is with compactness and…
Weakly supervised temporal action detection is a Herculean task in understanding untrimmed videos, since no supervisory signal except the video-level category label is available on training data. Under the supervision of category labels,…