Related papers: A Large-scale Comprehensive Dataset and Copy-overl…
Due to the costliness of labelled data in real-world applications, semi-supervised object detectors, underpinned by pseudo labelling, are appealing. However, handling confusing samples is nontrivial: discarding valuable confusing samples…
Natural language video localization (NLVL) is a crucial task in video understanding that aims to localize the target moment in videos specified by a given language description. Recently, a point-supervised paradigm has been presented to…
Detecting what has changed in an environment is essential for long-term autonomy, yet most change detection settings assume fixed viewpoints, mild misalignment, or only a few changed objects. We introduce Video-based Scene Change Detection…
Video super-resolution (VSR) aiming to reconstruct a high-resolution (HR) video from its low-resolution (LR) counterpart has made tremendous progress in recent years. However, it remains challenging to deploy existing VSR methods to…
Audio-visual source localization is a challenging task that aims to predict the location of visual sound sources in a video. Since collecting ground-truth annotations of sounding objects can be costly, a plethora of weakly-supervised…
CCTV safety monitoring demands anomaly detectors combine reliable clip-level accuracy with predictable per-clip latency despite weak supervision. This work investigates compact vision-language models (VLMs) as practical detectors for this…
Video object segmentation (VOS) aims at segmenting a particular object throughout the entire video clip sequence. The state-of-the-art VOS methods have achieved excellent performance (e.g., 90+% J&F) on existing datasets. However, since the…
We introduce a new task, named video corpus visual answer localization (VCVAL), which aims to locate the visual answer in a large collection of untrimmed instructional videos using a natural language question. This task requires a range of…
We introduce the Lecture Video Visual Objects (LVVO) dataset, a new benchmark for visual object detection in educational video content. The dataset consists of 4,000 frames extracted from 245 lecture videos spanning biology, computer…
Annotating videos with object segmentation masks typically involves a two stage procedure of drawing polygons per object instance for all the frames and then linking them through time. While simple, this is a very tedious, time consuming…
Unsupervised pixel-level video understanding remains challenging in real-world scenarios, where motion blur, occlusion, and fast object dynamics often cause temporal drift and flickering pseudo-labels.We propose VVitCutLER, an unsupervised…
Chapter generation becomes practical technique for online videos nowadays. The chapter breakpoints enable users to quickly find the parts they want and get the summative annotations. However, there is no public method and dataset for this…
Panoptic segmentation has become a new standard of visual recognition task by unifying previous semantic segmentation and instance segmentation tasks in concert. In this paper, we propose and explore a new video extension of this task,…
This paper tackles the problem of Cross-view Video-based camera Localization (CVL). The task is to localize a query camera by leveraging information from its past observations, i.e., a continuous sequence of images observed at previous time…
Dataset distillation methods reduce large-scale datasets to smaller sets of synthetic data, preserving sufficient information to quickly train a new model from scratch. However, prior work on dataset distillation has focused exclusively on…
Long video understanding poses a significant challenge for current Multi-modal Large Language Models (MLLMs). Notably, the MLLMs are constrained by their limited context lengths and the substantial costs while processing long videos.…
This paper proposes an attributable visual similarity learning (AVSL) framework for a more accurate and explainable similarity measure between images. Most existing similarity learning methods exacerbate the unexplainability by mapping each…
With the advancement of deep learning-driven video editing technology, security risks have emerged. Malicious video tampering can lead to public misunderstanding, property losses, and legal disputes. Currently, detection methods are mostly…
Video content comprehension is essential for various applications, ranging from video analysis to interactive systems. Despite advancements in large-scale vision-language models (VLMs), these models often struggle to capture the nuanced,…
Vision-Language Models pre-trained on large-scale image-text datasets have shown superior performance in downstream tasks such as image retrieval. Most of the images for pre-training are presented in the form of open domain common-sense…