TVM: A Tile-based Video Management Framework
Summary: TVM builds a workload-agnostic semantic index at tile granularity to avoid decoding/DNN inference on irrelevant video regions. It pairs an optimal index-construction using cost functions and pseudo-labels with query-driven parallel tile decoding and caching, yielding >5.6x throughput improvements. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Tianxiong Zhong
- 2. Zhiwei Zhang
- 3. Guo Lu
- 4. Ye Yuan
- 5. Yu-Ping Wang
- 6. Guoren Wang
Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 8,716 | nsDB: Architecting the Next Generation Database by Integrating Neural and Symbolic Systems | 2024 | VLDB | 4.4618187e-05 |
| 10,667 | Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse | 2025 | VLDB | 4.1945683e-05 |
Previous
Page 1 / 1
Next
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.
Previous
Page 1 / 1
Next