Related papers: Region-based Content Enhancement for Efficient Vid…
With the proliferation of video data in smart city applications like intelligent transportation, efficient video analytics has become crucial but also challenging. This paper proposes a semantics-driven cloud-edge collaborative approach for…
Video text spotting is still an important research topic due to its various real-applications. Previous approaches usually fall into the four-staged pipeline: text detection in individual images, framewisely recognizing localized text…
We present a new flow-based video completion algorithm. Previous flow completion methods are often unable to retain the sharpness of motion boundaries. Our method first extracts and completes motion edges, and then uses them to guide…
To enhance on-road environmental perception for autonomous driving, accurate and real-time analytics on high-resolution video frames generated from on-board cameras be-comes crucial. In this paper, we design a lightweight object location…
Data augmentation has recently emerged as an essential component of modern training recipes for visual recognition tasks. However, data augmentation for video recognition has been rarely explored despite its effectiveness. Few existing…
Precise boundary annotations of image regions can be crucial for downstream applications which rely on region-class semantics. Some document collections contain densely laid out, highly irregular and overlapping multi-class region instances…
The rapid evolution of multimedia and computer vision technologies requires adaptive visual model deployment strategies to effectively handle diverse tasks and varying environments. This work introduces AxiomVision, a novel framework that…
Visual document retrieval requires understanding heterogeneous and multi-modal content to satisfy implicit information needs. Recent advances use screenshot-based document encoding with fine-grained late interaction to encode holistic…
Robust scene segmentation and keyframe extraction are essential preprocessing steps in video understanding pipelines, supporting tasks such as indexing, summarization, and semantic retrieval. However, existing methods often lack…
We introduce ViDaS, a two-stream, fully convolutional Video, Depth-Aware Saliency network to address the problem of attention modeling ``in-the-wild", via saliency prediction in videos. Contrary to existing visual saliency approaches using…
With the recent growth of video-based Social Network Service (SNS) platforms, the demand for video editing among common users has increased. However, video editing can be challenging due to the temporally-varying factors such as camera…
Video-based person re-identification (Re-ID) aims at matching video sequences of pedestrians across non-overlapping cameras. It is a practical yet challenging task of how to embed spatial and temporal information of a video into its feature…
We present VEnhancer, a generative space-time enhancement framework that improves the existing text-to-video results by adding more details in spatial domain and synthetic detailed motion in temporal domain. Given a generated low-quality…
Although the problem of automatic video summarization has recently received a lot of attention, the problem of creating a video summary that also highlights elements relevant to a search query has been less studied. We address this problem…
Applying image processing algorithms independently to each frame of a video often leads to undesired inconsistent results over time. Developing temporally consistent video-based extensions, however, requires domain knowledge for individual…
The profound accumulation of precipitation during intense rainfall events can markedly degrade the quality of images, leading to the erosion of textural details. Despite the improvements observed in existing learning-based methods…
Recent advances in deep learning have markedly improved the quality of visual-attention modelling. In this work we apply these advances to video compression. We propose a compression method that uses a saliency model to adaptively compress…
Event cameras offer high temporal resolution and power efficiency, making them well-suited for edge AI applications. However, their high event rates present challenges for data transmission and processing. Subsampling methods provide a…
DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free approach to enhance the coherence and quality of DiT-based…
Remote sensing image change detection is of great importance in disaster assessment and urban planning. The mainstream method is to use encoder-decoder models to detect the change region of two input images. Since the change content of…