Tracker is a self-supervised VL tracker that uses a Dynamic Token Aggregation Module to learn instance tracking from single language descriptions in unlabeled videos and outperforms prior self-supervised methods.
Reversible unfold- ing network for concealed visual perception with generative refinement
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
other 1
citation-polarity summary
fields
cs.CV 5years
2026 5verdicts
UNVERDICTED 5representative citing papers
GS-STVSR achieves state-of-the-art continuous spatio-temporal video super-resolution quality with nearly constant inference time at standard scales and over 3x speedup at extreme scales using 2D Gaussian Splatting.
IQPIR uses NR-IQA-derived quality scores to condition a Transformer and dual-branch codebook for perceptually superior real-world image restoration.
RIDE applies Retinex-based homogeneous decomposition to improve foreground-background discriminability in concealed object segmentation tasks across multiple domains.
E²PO uses embedding-level perturbations to maintain intra-group variance and discriminative signal in RL-based preference optimization for generative flow models.
citing papers explorer
-
Learning to Track Instance from Single Nature Language Description
Tracker is a self-supervised VL tracker that uses a Dynamic Token Aggregation Module to learn instance tracking from single language descriptions in unlabeled videos and outperforms prior self-supervised methods.
-
GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting
GS-STVSR achieves state-of-the-art continuous spatio-temporal video super-resolution quality with nearly constant inference time at standard scales and over 3x speedup at extreme scales using 2D Gaussian Splatting.
-
Beyond Ground-Truth: Leveraging Image Quality Priors for Real-World Image Restoration
IQPIR uses NR-IQA-derived quality scores to condition a Transformer and dual-branch codebook for perceptually superior real-world image restoration.
-
RIDE: Retinex-Informed Decoupling for Exposing Concealed Objects
RIDE applies Retinex-based homogeneous decomposition to improve foreground-background discriminability in concealed object segmentation tasks across multiple domains.
-
Embedding-perturbed Exploration Preference Optimization for Flow Models
E²PO uses embedding-level perturbations to maintain intra-group variance and discriminative signal in RL-based preference optimization for generative flow models.