WSRVOS enables referring video object segmentation with text-only supervision by combining MLLM-based expression augmentation, multimodal feature interaction, pseudo-mask fusion, and temporal ranking constraints.
An image is worth 16x16 words: Transformers for image recognition at scale.ICLR
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SAT introduces density and isolation-based token aggregation to enable efficient global attention in super-resolution transformers, claiming up to 0.22 dB PSNR gain and 27% FLOP reduction over PFT.
citing papers explorer
-
Weakly-Supervised Referring Video Object Segmentation through Text Supervision
WSRVOS enables referring video object segmentation with text-only supervision by combining MLLM-based expression augmentation, multimodal feature interaction, pseudo-mask fusion, and temporal ranking constraints.
-
SAT: Selective Aggregation Transformer for Image Super-Resolution
SAT introduces density and isolation-based token aggregation to enable efficient global attention in super-resolution transformers, claiming up to 0.22 dB PSNR gain and 27% FLOP reduction over PFT.