Self-SiMS generates video moment candidates from intra-video self-similarity and re-ranks them with an MLLM, reporting state-of-the-art numbers on QVHighlights and mixed results on other benchmarks.
In: Proceedings of the IEEE/CVF International Conference on Computer Vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mitigating Modality and Language-Style Gaps for Zero-Shot Video Moment Retrieval
Self-SiMS generates video moment candidates from intra-video self-similarity and re-ranks them with an MLLM, reporting state-of-the-art numbers on QVHighlights and mixed results on other benchmarks.