Back to Projects
CompetitionCompleted
AIC25 COMPETITION
Led team SIU Cerberus at Ho Chi Minh City AI Challenge 2025, deploying the TARS (Temporal Alignment Retrieval System) framework for order-aware video event retrieval. Achieved 93.15% accuracy on the benchmark with a training-free monotonic DP alignment approach.
Key Details
Designed and led implementation of TARS: a training-free, order-aware video retrieval system decomposing queries into ordered sub-event sequences.
Monotonic dynamic-programming alignment enforcing strict temporal ordering at inference time with O(nm) time and O(m) memory complexity.
Complementary vision-language encoders reducing sensitivity to individual encoder weaknesses across diverse query types.
Two-stage retrieve-then-rerank pipeline: FAISS coarse retrieval followed by TARS re-ranking for precision-latency balance.
Highlights
- •93.15% accuracy on HCM AI Challenge 2025
- •Training-free temporal alignment via monotonic DP
- •Query decomposed into ordered sub-event sequences
- •O(nm) time complexity per video shot
Technologies
PythonPyTorchFAISSCLIPGoogle GeminiNumPyFFmpeg