Search papers, labs, and topics across Lattice.
Affiliation:
2
0
4
TAME achieves a 4.0 increase in retrieval accuracy on MSR-VTT by effectively modeling temporal dynamics in video data, outpacing traditional CLIP-based approaches.
MARS unlocks the hidden potential of multimodal embeddings, achieving state-of-the-art text-video retrieval by capturing nuanced similarities that traditional methods miss.