Search papers, labs, and topics across Lattice.
University of Science and Technology of China
2
0
4
Forget monolithic sentiment vectors: PRISM adaptively fuses multimodal cues by comparing them in a shared prototype space, leading to state-of-the-art sentiment analysis.
Forget coarse-grained audio-visual tasks: RA-SSU offers frame-level sound source understanding with two new datasets and a transformer-based benchmark.