Deja Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse

Authors

• 1. Jinwoo Hwang (Korea Advanced Institute of Science and Technology)
• 2. Daeun Kim (Korea Advanced Institute of Science and Technology)
• 3. Sangyeop Lee (Korea Advanced Institute of Science and Technology)
• 4. Yoonsung Kim (Korea Advanced Institute of Science and Technology)
• 5. Guseul Heo (Korea Advanced Institute of Science and Technology)
• 6. Hojoon Kim (Korea Advanced Institute of Science and Technology)
• 7. Yunseok Jeong (Korea Advanced Institute of Science and Technology)
• 8. Tadiwos Meaza (Korea Advanced Institute of Science and Technology)
• 9. Eunhyeok Park (Pohang University of Science and Technology)
• 10. Jeongseob Ahn (Korea University)
• 11. Jongse Park (Korea Advanced Institute of Science and Technology)

@article{hwang_vldb25,
        title = {{Deja Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse}},
        author = {Hwang, Jinwoo and Kim, Daeun and Lee, Sangyeop and Kim, Yoonsung and Heo, Guseul and Kim, Hojoon and Jeong, Yunseok and Meaza, Tadiwos and Park, Eunhyeok and Ahn, Jeongseob and Park, Jongse},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {10},
        pages = {3284--3298},
        doi = {10.14778/3748191.3748195},
        url = {https://doi.org/10.14778/3748191.3748195},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Outgoing Citations (Sorted by Pagerank)

Showing 23 of 23 cited papers.

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

Semantically Similar Papers