Query-Aware Path Inference from Spatial Videos

Summary: Query-aware framework that avoids exhaustive trajectory reconstruction by retrieving only query-relevant snapshots via a similarity index and modeling transitions with a probability motion graph. Adds high-order spatio-temporal dependency constraints for global consistency; outperforms baselines on real and synthetic urban-video benchmarks in accuracy and efficiency. (summarized by gpt-5-mini on Feb 11 2026)

Paper ID: 7603
Venue: SIGMOD
Year: 2026
Pagerank: 5.093636e-05
Overall Rank: 10,393 | 28.70%
DOI: 10.1145/3769817

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Taihang Dong (Zhejiang University)
2. Dingyu Yang (Zhejiang University)
3. Ping Chen (Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security; Zhejiang Lab; Zhejiang University)
4. Dongxiang Zhang (Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security; Zhejiang University)

BibTeX Citation

@inproceedings{dong_sigmod26,
        title = {{Query-Aware Path Inference from Spatial Videos}},
        author = {Dong, Taihang and Yang, Dingyu and Chen, Ping and Zhang, Dongxiang},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3769817},
        url = {https://dl.acm.org/doi/10.1145/3769817},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank

Outgoing Citations (Sorted by Pagerank)

Showing 11 of 11 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
3,365	Spatial and Temporal Constrained Ranked Retrieval over Videos	2022	VLDB	7.4763252e-05
3,756	Vaas: Video Analytics At Scale	2020	VLDB	7.1487427e-05
3,875	Visual Road: A Video Data Management Benchmark	2019	SIGMOD	7.0557272e-05
4,007	Optimizing Video Analytics with Declarative Model Relationships	2023	VLDB	6.9632395e-05
7,240	Randomized Algorithms Accelerated over CPU-GPU for Ultra-High Dimensional Similarity Search	2018	SIGMOD	5.6643589e-05
8,518	DeepVQL: Deep Video Queries on PostgreSQL	2023	VLDB	5.4119882e-05
9,894	Co-movement Pattern Mining from Videos	2024	VLDB	5.1997534e-05
9,925	DoveDB: A Declarative and Low-Latency Video Database	2023	VLDB	5.1955087e-05
10,791	High-Throughput Ingestion for Video Warehouse: Comprehensive Configuration and Effective Exploration	2025	SIGMOD	5.093636e-05
10,841	Mining Platoon Patterns from Traffic Videos	2025	VLDB	5.093636e-05
11,162	Predictive and Near-Optimal Sampling for View Materialization in Video Databases	2024	SIGMOD	5.093636e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	7,463	Effectively Indexing Uncertain Moving Objects for Predictive Queries	2009	VLDB
2	6,953	Trajectory Similarity Measurement: An Efficiency Perspective	2024	VLDB
3	7,669	Multi-Modal Transportation Recommendation with Unified Route Representation Learning	2021	VLDB
4	3,365	Spatial and Temporal Constrained Ranked Retrieval over Videos	2022	VLDB
5	10,801	Revisiting CNNs for Trajectory Similarity Learning	2025	VLDB
6	6,579	A Deep Generative Model for Trajectory Modeling and Utilization	2023	VLDB
7	10,841	Mining Platoon Patterns from Traffic Videos	2025	VLDB
8	9,894	Co-movement Pattern Mining from Videos	2024	VLDB
9	5,112	Fast Large-Scale Trajectory Clustering	2020	VLDB
10	4,429	Evaluating Temporal Queries Over Video Feeds	2021	SIGMOD