Video Grounding

The Kinetics dataset is a large-scale, high-quality dataset for human action recognition in videos. The dataset consists of around 500,000 video clips covering 600 human action classes with at least 600 video clips for each action class. Each video clip lasts around 10 seconds and is labeled with a single action class. The videos are collected from YouTube. Source: Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey

The Query-based Video Highlights (QVHighlights) dataset is a dataset for detecting customized moments and highlights from videos given natural language (NL). It consists of over 10,000 YouTube videos, covering a wide range of topics, from everyday activities and travel in lifestyle vlog videos to social and political activities in news videos. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w.r.t. the query, and (3) five-point scale saliency scores for all query-relevant clips.

MAD (Movie Audio Descriptions) is an automatically curated large-scale dataset for the task of natural language grounding in videos or natural language moment retrieval. MAD exploits available audio descriptions of mainstream movies. Such audio descriptions are redacted for visually impaired audiences and are therefore highly descriptive of the visual content being displayed. MAD contains over 384,000 natural language sentences grounded in over 1,200 hours of video, and provides a unique setup for video grounding as the visual stream is truly untrimmed with an average video duration of 110 minutes. 2 orders of magnitude longer than legacy datasets. Take a look at the paper for additional information. From the authors on availability: "Due to copyright constraints, MAD’s videos will not be publicly released. However, we will provide all necessary features for our experiments’ reproducibility and promote future research in this direction"

Animal Kingdom is a large and diverse dataset that provides multiple annotated tasks to enable a more thorough understanding of natural animal behaviors. The wild animal footage used in the dataset records different times of the day in an extensive range of environments containing variations in backgrounds, viewpoints, illumination and weather conditions. More specifically, the dataset contains 50 hours of annotated videos to localize relevant animal behavior segments in long videos for the video grounding task, 30K video sequences for the fine-grained multi-label action recognition task, and 33K frames for the pose estimation task, which correspond to a diverse range of animals with 850 species across 6 major animal classes.

How to capture the present knowledge from surrounding situations and perform reasoning accordingly is crucial and challenging for machine intelligence. STAR Benchmark is a novel benchmark for Situated Reasoning, which provides 60K challenging situated questions in four types of tasks, 140K situated hypergraphs, symbolic situation programs, and logic-grounded diagnosis for real-world video situations. (Data Download, STAR Leaderboard)

Are current 3D object tracking methods truely robust enough for low-fidelity depth sensors like the iPhone LiDAR? We introduce DTTD-Mobile (fully compatible w/ YCB toolbox), a new benchmark built on real-world data captured from mobile devices; 18 objects observed in 100 videos with 47,668 sampled frames and 114,143 object annotations. We evaluate several popular methods—including BundleSDF, ES6D, MegaPose, and DenseFusion—and highlight their limitations in this challenging setting. Keywords: ObjectPoseEstimation, MobileAI, EdgeAI, ARVR, CVPR

Video Localized Narratives is a new form of multimodal video annotations connecting vision and language. The annotations are created from videos with Localized Narratives, capturing even complex events involving multiple actors interacting with each other and with several passive objects. It contains annotations of 20k videos of the OVIS, UVO, and Oops datasets, totalling 1.7M words. Source: Connecting Vision and Language with Video Localized Narratives Image Source: https://arxiv.org/pdf/2302.11217v1.pdf

Despite impressive advancements in video understanding, most efforts remain limited to coarse-grained or visual-only video tasks. However, real-world videos encompass omni-modal information (vision, audio, and speech) with a series of events forming a cohesive storyline. The lack of multi-modal video data with fine-grained event annotations and the high cost of manual labeling are major obstacles to comprehensive omni-modality video perception. To address this gap, we propose an automatic pipeline consisting of high-quality multi-modal video filtering, semantically coherent omni-modal event boundary detection, and cross-modal correlation-aware event captioning. In this way, we present LongVALE, the first-ever Vision-Audio-Language Event understanding benchmark comprising 105K omni-modal events with precise temporal boundaries and detailed relation-aware captions within 8.4K high-quality long videos. Further, we build a baseline that leverages LongVALE to enable video large language models (LLMs) for omni-modality fine-grained temporal video understanding for the first time. Extensive experiments demonstrate the effectiveness and great potential of LongVALE in advancing comprehensive multi-modal video understanding.

Kinetics-GEB+ (Generic Event Boundary Captioning, Grounding and Retrieval) is a dataset that consists of over 170k boundaries associated with captions describing status changes in the generic events in 12K videos.

YouwikiHow is a dataset for Weakly-Supervised temporal Article Grounding (WSAG). It contains 47K videos and an average of 20.8 query sentences for each video. Source: Weakly-Supervised Temporal Article Grounding Image Source: https://arxiv.org/pdf/2210.12444v1.pdf

We construct a fine-grained video-text dataset with 12K annotated high-resolution videos (~400k clips). The annotation of this dataset is inspired by the video script. If we want to make a video, we have to first write a script to organize how to shoot the scenes in the videos. To shoot a scene, we need to decide the content, shot type (medium shot, close-up, etc), and how the camera moves (panning, tilting, etc). Therefore, we extend video captioning to video scripting by annotating the videos in the format of video scripts. Different from the previous video-text datasets, we densely annotate the entire videos without discarding any scenes and each scene has a caption with ~145 words. Besides the vision modality, we transcribe the voice-over into text and put it along with the video title to give more background information for annotating the videos. In addition, we propose Vript-Bench, a new benchmark consisting of three challenging video understanding tasks (which are carefully double-checked by humans): - Vript-CAP (Caption): A benchmark with detailed captions rather than short captions. - Vript-RR (Retrieve then Reason): A video reasoning benchmark by first giving a detailed description of the scene as a hint and then asking questions about details in the scene. - Vript-ERO (Event Re-ordering): A benchmark that tests the temporal understanding by offering the descriptions of scenes located in two/four different timelines of the same video, and asks the model to give the right temporal order of the scenes.