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...

Deskribapen osoa

Xehetasun bibliografikoak
Egile Nagusiak:	Yang, Z, Wang, J, Ye, X, Tang, Y, Chen, K, Zhao, H, Torr, PHS
Formatua:	Journal article
Hizkuntza:	English
Argitaratua:	IEEE 2024

Antzeko izenburuak

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

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

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

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

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

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

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

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

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

Geometric motion segmentation and model selection
nork: Torr, PHS
Argitaratua: (1998)

Reference-aware language models
nork: Yang, Z, et al.
Argitaratua: (2017)

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

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

Outlier detection and motion segmentation
nork: Torr, PHS, et al.
Argitaratua: (1993)

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

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

Vision transformer with progressive sampling
nork: Yue, X, et al.
Argitaratua: (2022)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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