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...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριοι συγγραφείς:	Yang, Z, Wang, J, Ye, X, Tang, Y, Chen, K, Zhao, H, Torr, PHS
Μορφή:	Journal article
Γλώσσα:	English
Έκδοση:	IEEE 2024

Παρόμοια τεκμήρια

LAVT: Language-Aware Vision Transformer for referring image segmentation
ανά: Yang, Z, κ.ά.
Έκδοση: (2022)

Semantics-aware dynamic localization and refinement for referring image segmentation
ανά: Yang, Z, κ.ά.
Έκδοση: (2023)

Vision transformers: from semantic segmentation to dense prediction
ανά: Zhang, L, κ.ά.
Έκδοση: (2024)

Hierarchical interaction network for video object segmentation from referring expressions
ανά: Yang, Z, κ.ά.
Έκδοση: (2021)

Behind every domain there is a shift: adapting distortion-aware vision transformers for panoramic semantic segmentation
ανά: Zhang, J, κ.ά.
Έκδοση: (2024)

LUNA: language as continuing anchors for referring expression comprehension
ανά: Liang, Y, κ.ά.
Έκδοση: (2023)

Behind every domain there is a shift: adapting distortion-aware vision transformers for panoramic semantic segmentation
ανά: Zhang, J, κ.ά.
Έκδοση: (2024)

An empirical study of detection-based video instance segmentation
ανά: Wang, Q, κ.ά.
Έκδοση: (2020)

Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers
ανά: Zheng, S, κ.ά.
Έκδοση: (2021)

Geometric motion segmentation and model selection
ανά: Torr, PHS
Έκδοση: (1998)

Reference-aware language models
ανά: Yang, Z, κ.ά.
Έκδοση: (2017)

Unifying training and inference for panoptic segmentation
ανά: Li, Q, κ.ά.
Έκδοση: (2020)

Dynamic graph cuts and their applications in computer vision
ανά: Kohli, P, κ.ά.
Έκδοση: (2010)

Outlier detection and motion segmentation
ανά: Torr, PHS, κ.ά.
Έκδοση: (1993)

Patch-based separable transformer for visual recognition
ανά: Sun, S, κ.ά.
Έκδοση: (2022)

Semantic-aware auto-encoders for self-supervised representation learning
ανά: Wang, G, κ.ά.
Έκδοση: (2022)

Vision transformer with progressive sampling
ανά: Yue, X, κ.ά.
Έκδοση: (2022)

Improving few-shot learning by spatially-aware matching and crosstransformer
ανά: Zhang, H, κ.ά.
Έκδοση: (2023)

Concerning Bayesian motion segmentation, model averaging, matching and the trifocal tensor
ανά: Torr, PHS, κ.ά.
Έκδοση: (2006)

Bottom-up Instance Segmentation using Deep Higher-Order CRFs
ανά: Arnab, A, κ.ά.
Έκδοση: (2016)

An object category specific mrf for segmentation
ανά: Kumar, MP, κ.ά.
Έκδοση: (2007)

Learning layered motion segmentations of video
ανά: Kumar, MP, κ.ά.
Έκδοση: (2005)

On the robustness of semantic segmentation models to adversarial attacks
ανά: Arnab, A, κ.ά.
Έκδοση: (2019)

SegPGD: an effective and efficient adversarial attack for evaluating and boosting segmentation robustness
ανά: Gu, J, κ.ά.
Έκδοση: (2022)

Target identity-aware network flow for online multiple target tracking
ανά: Dehghan, A, κ.ά.
Έκδοση: (2015)

Learning layered motion segmentations of video
ανά: Pawan Kumar, M, κ.ά.
Έκδοση: (2007)

Urban 3D semantic modelling using stereo vision
ανά: Sengupta, S, κ.ά.
Έκδοση: (2013)

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

Discovering class-specific pixels for weakly-supervised semantic segmentation
ανά: Chaudhry, A, κ.ά.
Έκδοση: (2017)

OBJCUT: efficient segmentation using top-down and bottom-up cues
ανά: Kumar, MP, κ.ά.
Έκδοση: (2009)

Practical Techniques for Vision-Language Segmentation Model in Remote Sensing
ανά: Y. Lin, κ.ά.
Έκδοση: (2024-06-01)

Benchmarking robustness of adaptation methods on pre-trained vision-language models
ανά: Chen, S, κ.ά.
Έκδοση: (2024)

Occluded video instance segmentation: A benchmark
ανά: Qi, J, κ.ά.
Έκδοση: (2022)

GeoNet++: Iterative geometric neural network with edge-aware refinement for joint depth and surface normal estimation
ανά: Qi, X, κ.ά.
Έκδοση: (2020)

Scalable cascade inference for semantic image segmentation
ανά: Sturgess, P, κ.ά.
Έκδοση: (2012)

POSECUT: simultaneous segmentation and 3d pose estimation of humans using dynamic graph-cuts
ανά: Bray, M, κ.ά.
Έκδοση: (2006)

Deep FusionNet for point cloud semantic segmentation
ανά: Zhang, F, κ.ά.
Έκδοση: (2020)

Associative hierarchical CRFs for object class image segmentation
ανά: Ladický, L, κ.ά.
Έκδοση: (2009)

Prompting a pretrained transformer can be a universal approximator
ανά: Petrov, A, κ.ά.
Έκδοση: (2024)

Spatio-temporal action instance segmentation and localisation
ανά: Saha, S, κ.ά.
Έκδοση: (2020)