Video Retrieval
Video retrieval is a subtask in the field of computer vision, aiming to select the video that best matches a given text query from a pool of candidate videos. Typically, the results of video retrieval are returned in the form of a ranked list and evaluated using document retrieval metrics. This task has significant application value in areas such as multimedia information retrieval, video surveillance, and content recommendation.
MSR-VTT-1kA
HunYuan_tvr
DiDeMo
InternVideo
MSR-VTT
Text-Video Embedding
LSMDC
CAMoE
ActivityNet
Ours
MSVD
HunYuan_tvr
FIVR-200K
S2VS
YouCook2
COOT
VATEX
LAFF
QuerYD
SSv2-label retrieval
SSv2-template retrieval
UMT-L (ViT-L/16)
Condensed Movies
TESTA (ViT-B/16)
EgoExoLearn
TGIF
TVR
Hero w/ pre-training
Charades-STA
PO Loss
MSVD-Indonesian
X-CLIP (Cross-Lingual)
RUDDER
PO Loss