Related papers: Beyond Rigid: Benchmarking Non-Rigid Video Editing
We developed REVEX, a removal-based video explanations framework. This work extends fine-grained explanation frameworks for computer vision data and adapts six existing techniques to video by adding temporal information and local…
Video editing is a challenging task that requires manipulating videos on both the spatial and temporal dimensions. Existing methods for video editing mainly focus on changing the appearance or style of the objects in the video, while…
The In-context generation paradigm recently has demonstrated strong power in instructional image editing with both data efficiency and synthesis quality. Nevertheless, shaping such in-context learning for instruction-based video editing is…
Anomaly detection in videos has been attracting an increasing amount of attention. Despite the competitive performance of recent methods on benchmark datasets, they typically lack desirable features such as modularity, cross-domain…
Generating free-viewpoint videos is critical for immersive VR/AR experience but recent neural advances still lack the editing ability to manipulate the visual perception for large dynamic scenes. To fill this gap, in this paper we propose…
Visual reasoning, the capability to interpret visual input in response to implicit text query through multi-step reasoning, remains a challenge for deep learning models due to the lack of relevant benchmarks. Previous work in visual…
Video understanding, including video captioning and retrieval, is still a great challenge for video-language models (VLMs). The existing video retrieval and caption benchmarks only include short descriptions, limits their ability of…
Recent text-to-video generation models have made remarkable progress in visual realism, motion fidelity, and text-video alignment, yet they still struggle to produce socially coherent behavior. Unlike humans, who readily infer intentions,…
Multimodal Large Language Models have achieved strong performance in single-video understanding, yet their ability to reason across multiple videos remains limited. Existing approaches typically concatenate multiple videos into a single…
Instruction-guided image editing has seen remarkable progress with models like FLUX.2 and Qwen-Image-Edit, yet they still struggle with complex scenarios with multiple similar instances each requiring individual edits. We observe that…
Significant progress has been made in the field of Instruction-based Image Editing (IIE). However, evaluating these models poses a significant challenge. A crucial requirement in this field is the establishment of a comprehensive evaluation…
Recent advances in text-driven image editing have been significant, yet the task of accurately evaluating these edited images continues to pose a considerable challenge. Different from the assessment of text-driven image generation,…
Most existing video anomaly detectors rely solely on RGB frames, which lack the temporal resolution needed to capture abrupt or transient motion cues, key indicators of anomalous events. To address this limitation, we propose Image-Event…
Over the last decade, online lecture videos have become increasingly popular and have experienced a meteoric rise during the pandemic. However, video-language research has primarily focused on instructional videos or movies, and tools to…
Existing AI-generated video quality assessment (AIGVQA) methods mainly focus on global perceptual realism and coarse text-video alignment, while overlooking a critical requirement in educational scenarios: concept correctness. In early…
How far are deep models from real-world video anomaly understanding (VAU)? Current works typically emphasize on detecting unexpected occurrences deviated from normal patterns or comprehending anomalous events with interpretable…
We introduce CameraBench, a large-scale dataset and benchmark designed to assess and improve camera motion understanding. CameraBench consists of ~3,000 diverse internet videos, annotated by experts through a rigorous multi-stage quality…
Almost all digital videos are coded into compact representations before being transmitted. Such compact representations need to be decoded back to pixels before being displayed to humans and - as usual - before being enhanced/analyzed by…
Humans watch more than a billion hours of video per day. Most of this video was edited manually, which is a tedious process. However, AI-enabled video-generation and video-editing is on the rise. Building on text-to-image models like Stable…
Video understanding requires models to continuously track and update world state during playback. While existing benchmarks have advanced video understanding evaluation across multiple dimensions, the observation of how models maintain…