Language-aware vision transformer for referring segmentation

Language-aware vision transformer for referring segmentation

Referring segmentation is a fundamental vision-language task that aims to segment out an object from an image or video in accordance with a natural language description. One of the key challenges behind this task is leveraging the referring expression for highlighting relevant positions in the image...

Disgrifiad llawn

Manylion Llyfryddiaeth
Prif Awduron:	Yang, Z, Wang, J, Ye, X, Tang, Y, Chen, K, Zhao, H, Torr, PHS
Fformat:	Journal article
Iaith:	English
Cyhoeddwyd:	IEEE 2024

Eitemau Tebyg

LAVT: Language-Aware Vision Transformer for referring image segmentation
gan: Yang, Z, et al.
Cyhoeddwyd: (2022)

Semantics-aware dynamic localization and refinement for referring image segmentation
gan: Yang, Z, et al.
Cyhoeddwyd: (2023)

Vision transformers: from semantic segmentation to dense prediction
gan: Zhang, L, et al.
Cyhoeddwyd: (2024)

Hierarchical interaction network for video object segmentation from referring expressions
gan: Yang, Z, et al.
Cyhoeddwyd: (2021)

Behind every domain there is a shift: adapting distortion-aware vision transformers for panoramic semantic segmentation
gan: Zhang, J, et al.
Cyhoeddwyd: (2024)

LUNA: language as continuing anchors for referring expression comprehension
gan: Liang, Y, et al.
Cyhoeddwyd: (2023)

Behind every domain there is a shift: adapting distortion-aware vision transformers for panoramic semantic segmentation
gan: Zhang, J, et al.
Cyhoeddwyd: (2024)

An empirical study of detection-based video instance segmentation
gan: Wang, Q, et al.
Cyhoeddwyd: (2020)

Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers
gan: Zheng, S, et al.
Cyhoeddwyd: (2021)

Geometric motion segmentation and model selection
gan: Torr, PHS
Cyhoeddwyd: (1998)

Reference-aware language models
gan: Yang, Z, et al.
Cyhoeddwyd: (2017)

Unifying training and inference for panoptic segmentation
gan: Li, Q, et al.
Cyhoeddwyd: (2020)

Dynamic graph cuts and their applications in computer vision
gan: Kohli, P, et al.
Cyhoeddwyd: (2010)

Outlier detection and motion segmentation
gan: Torr, PHS, et al.
Cyhoeddwyd: (1993)

Patch-based separable transformer for visual recognition
gan: Sun, S, et al.
Cyhoeddwyd: (2022)

Semantic-aware auto-encoders for self-supervised representation learning
gan: Wang, G, et al.
Cyhoeddwyd: (2022)

Vision transformer with progressive sampling
gan: Yue, X, et al.
Cyhoeddwyd: (2022)

Improving few-shot learning by spatially-aware matching and crosstransformer
gan: Zhang, H, et al.
Cyhoeddwyd: (2023)

Concerning Bayesian motion segmentation, model averaging, matching and the trifocal tensor
gan: Torr, PHS, et al.
Cyhoeddwyd: (2006)

Bottom-up Instance Segmentation using Deep Higher-Order CRFs
gan: Arnab, A, et al.
Cyhoeddwyd: (2016)

An object category specific mrf for segmentation
gan: Kumar, MP, et al.
Cyhoeddwyd: (2007)

Learning layered motion segmentations of video
gan: Kumar, MP, et al.
Cyhoeddwyd: (2005)

On the robustness of semantic segmentation models to adversarial attacks
gan: Arnab, A, et al.
Cyhoeddwyd: (2019)

SegPGD: an effective and efficient adversarial attack for evaluating and boosting segmentation robustness
gan: Gu, J, et al.
Cyhoeddwyd: (2022)

Target identity-aware network flow for online multiple target tracking
gan: Dehghan, A, et al.
Cyhoeddwyd: (2015)

Learning layered motion segmentations of video
gan: Pawan Kumar, M, et al.
Cyhoeddwyd: (2007)

Object-aware vision and language navigation for domestic robots
gan: Zhao, Weiyi
Cyhoeddwyd: (2022)

Urban 3D semantic modelling using stereo vision
gan: Sengupta, S, et al.
Cyhoeddwyd: (2013)

Discovering class-specific pixels for weakly-supervised semantic segmentation
gan: Chaudhry, A, et al.
Cyhoeddwyd: (2017)

Practical Techniques for Vision-Language Segmentation Model in Remote Sensing
gan: Y. Lin, et al.
Cyhoeddwyd: (2024-06-01)

Benchmarking robustness of adaptation methods on pre-trained vision-language models
gan: Chen, S, et al.
Cyhoeddwyd: (2024)

OBJCUT: efficient segmentation using top-down and bottom-up cues
gan: Kumar, MP, et al.
Cyhoeddwyd: (2009)

Occluded video instance segmentation: A benchmark
gan: Qi, J, et al.
Cyhoeddwyd: (2022)

GeoNet++: Iterative geometric neural network with edge-aware refinement for joint depth and surface normal estimation
gan: Qi, X, et al.
Cyhoeddwyd: (2020)

Scalable cascade inference for semantic image segmentation
gan: Sturgess, P, et al.
Cyhoeddwyd: (2012)

POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts
gan: Bray, M, et al.
Cyhoeddwyd: (2006)

Deep FusionNet for point cloud semantic segmentation
gan: Zhang, F, et al.
Cyhoeddwyd: (2020)

Associative hierarchical CRFs for object class image segmentation
gan: Ladický, L, et al.
Cyhoeddwyd: (2009)

Automatic Medical Image Segmentation with Vision Transformer
gan: Jie Zhang, et al.
Cyhoeddwyd: (2024-03-01)

Wildfire Segmentation Using Deep Vision Transformers
gan: Rafik Ghali, et al.
Cyhoeddwyd: (2021-09-01)