An official website of the United States government
Localizing video moments based on the movement patterns of objects is an important task in video analytics. Existing video analytics systems offer two types of querying interfaces based on natural language and SQL, respectively. However, both types of interfaces have major limitations. SQL-based systems require high query specification time, whereas natural language-based systems require large training datasets to achieve satisfactory retrieval accuracy. To address these limitations, we present SketchQL, a video database management system (VDBMS) for offline, exploratory video moment retrieval that is both easy to use and generalizes well across multiple video moment datasets. To improve ease-of-use, SketchQL features avisual query interfacethat enables users to sketch complex visual queries through intuitive drag-and-drop actions. To improve generalizability, SketchQL operates on object-tracking primitives that are reliably extracted across various datasets using pre-trained models. We present a learned similarity search algorithm for retrieving video moments closely matching the user's visual query based on object trajectories. SketchQL trains the model on a diverse dataset generated with a novel simulator, that enhances its accuracy across a wide array of datasets and queries. We evaluate SketchQL on four real-world datasets with nine queries, demonstrating its superior usability and retrieval accuracy over state-of-the-art VDBMSs.
more »
« less
This content will become publicly available on August 1, 2025
SketchQL Demonstration: Zero-Shot Video Moment Querying with Sketches
In this paper, we will present SketchQL, a video database management system (VDBMS) for retrieving video moments with a sketch-based query interface. This novel interface allows users to specify object trajectory events with simple mouse drag-and-drop operations. Users can use trajectories of single objects as building blocks to compose complex events. Using a pre-trained model that encodes trajectory similarity, SketchQL achieves zero-shot video moments retrieval by performing similarity searches over the video to identify clips that are the most similar to the visual query. In this demonstration, we introduce the graphic user interface of SketchQL and detail its functionalities and interaction mechanisms. We also demonstrate the end-to-end usage of SketchQL from query composition to video moments retrieval using real-world scenarios.
more »
« less
- PAR ID:
- 10566575
- Publisher / Repository:
- VLDB
- Date Published:
- Journal Name:
- Proceedings of the VLDB Endowment
- Volume:
- 17
- Issue:
- 12
- ISSN:
- 2150-8097
- Page Range / eLocation ID:
- 4429 to 4432
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Commercial image search applications like eBay and Pinterest allow users to select the focused area as bounding box over the query images, which improves the retrieval accuracy. The focused area image retrieval strategy motivated our research, but our system has three main advantages over the existing works. (1) Given a query focus area, our approach localizes the most similar region in the database image and only this region is used for computing image similarity. This is done in a unified network whose weights are adjusted both for localization and similarity learning in an end-to-end manner. (2) This is achieved using fewer than five proposals extracted from a saliency map, which speedups the pairwise similarity computation. Usually hundreds or even thousands of proposals are used for localization. (3) For users, our system explains the relevance of the retrieved results by locating the regions in database images most similar to query object. Our method achieves significantly better retrieval performance than the off-the-shelf object localization-based retrieval methods and end-to-end trained triplet method with a region proposal network. Our experimental results demonstrate 86% retrieval rate as compared to 73% achieved by the existing methods on PASCAL VOC07 and VOC12 datasets. Extensive experiments are also conducted on the instance retrieval databases Oxford5k and INSTRE, wherewe exhibit competitive performance. Finally, we provide both quantitative and qualitative results of our retrieval method demonstrating its superiority over commercial image search systems.more » « less
-
null (Ed.)Traffic event retrieval is one of the important tasks for intelligent traffic system management. To find accurate candidate events in traffic videos corresponding to a specific text query, it is necessary to understand the text query's attributes, represent the visual and motion attributes of vehicles in videos, and measure the similarity between them. Thus we propose a promising method for vehicle event retrieval from a natural-language-based specification. We utilize both appearance and motion attributes of a vehicle and adapt the COOT model to evaluate the semantic relationship between a query and a video track. Experiments with the test dataset of Track 5 in AI City Challenge 2021 show that our method is among the top 6 with a score of 0.1560.more » « less
-
We address the problem of retrieving a specific moment from an untrimmed video by a query sentence. This is a challenging problem because a target moment may take place in relations to other temporal moments in the untrimmed video. Existing methods cannot tackle this challenge well since they consider temporal moments individually and neglect the temporal dependencies. In this paper, we model the temporal relations between video moments by a two-dimensional map, where one dimension indicates the starting time of a moment and the other indicates the end time. This 2D temporal map can cover diverse video moments with different lengths, while representing their adjacent relations. Based on the 2D map, we propose a Temporal Adjacent Network (2D-TAN), a single-shot framework for moment localization. It is capable of encoding the adjacent temporal relation, while learning discriminative features for matching video moments with referring expressions. We evaluate the proposed 2D-TAN on three challenging benchmarks, i.e., Charades-STA, ActivityNet Captions, and TACoS, where our 2D-TAN outperforms the state-of-the-art.more » « less
-
Retrieval-augmented generation (RAG) systems can effectively address user queries by leveraging indexed document corpora to retrieve the relevant contexts. Ranking techniques have been adopted in RAG systems to sort the retrieved contexts by their relevance to the query so that users can select the most useful contexts for their downstream tasks. While many existing ranking methods rely on the similarity between the embedding vectors of the context and query to measure relevance, it is important to note that similarity does not equate to relevance in all scenarios. Some ranking methods use large language models (LLMs) to rank the contexts by putting the query and the candidate contexts in the prompt and asking LLM about their relevance. The scalability of those methods is contingent on the number of candidate contexts and the context window of those LLMs. Also, those methods require fine-tuning the LLMs, which can be computationally expensive and require domain-related data. In this work, we propose a scalable ranking framework that does not involve LLM training. Our framework uses an off-the-shelf LLM to hypothesize the user's query based on the retrieved contexts and ranks the contexts based on the similarity between the hypothesized queries and the user query. Our framework is efficient at inference time and is compatible with many other context retrieval and ranking techniques. Experimental results show that our method improves the ranking performance of retrieval systems in multiple benchmarks.more » « less
