Tencent-MVSE: A Large-Scale Benchmark Dataset for Multi-Modal Video Similarity Evaluation.
Zhaoyang ZengYongsheng LuoZhenhua LiuFengyun RaoDian LiWeidong GuoZhen WenPublished in: CVPR (2022)
Keyphrases
- multi modal
- benchmark datasets
- video search
- semantic concepts
- similarity measure
- multiple modalities
- multi modality
- multimedia
- cross modal
- semantic similarity
- video content
- video sequences
- audio visual
- video data
- high dimensional
- video streams
- video clips
- image processing
- fusing multiple
- image annotation
- video frames
- video database
- visual cues
- video shots
- medical images
- uni modal