paper-with-me

홈 › Papers

Segment-Phrase Table for Semantic Segmentation, Visual Entailment and Paraphrasing

2015-09-27 · ICCV 2015 12 · Hamid Izadinia, Fereshteh Sadeghi, Santosh Kumar Divvala, Yejin Choi, Ali Farhadi

We introduce Segment-Phrase Table (SPT), a large collection of bijective associations between textual phrases and their corresponding segmentations. Leveraging recent progress in object recognition and natural language semantics, we show how we can successfully build a high-quality segment-phrase table using minimal human supervision. More importantly, we demonstrate the unique value unleashed by this rich bimodal resource, for both vision as well as natural language understanding. First, we show that fine-grained textual labels facilitate contextual reasoning that helps in satisfying semantic constraints across image segments. This feature enables us to achieve state-of-the-art segmentation results on benchmark datasets. Next, we show that the association of high-quality segmentations to textual phrases aids in richer semantic understanding and reasoning of these textual phrases. Leveraging this feature, we motivate the problem of visual entailment and visual paraphrasing, and demonstrate its utility on a large dataset.

📄 PDF Abstract BibTeX arXiv:1509.08075

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language UnderstandingObject RecognitionSemantic SegmentationVisual Entailment

Similar Papers 제목 키워드 기반

PPMN: Pixel-Phrase Matching Network for One-Stage Panoptic Narrative Grounding

2022-08-11 · Zihan Ding, Zi-han Ding, Tianrui Hui, Junshi Huang 외

Panoptic Narrative Grounding (PNG) is an emerging task whose goal is to segment visual objects of things and stuff categories described by dense narrative captions of a still image. The previous two-stage approach first …

Panoptic SegmentationSegmentationSemantic correspondence

Segmentation from Natural Language Expressions

2016-03-20 · Ronghang Hu, Marcus Rohrbach, Trevor Darrell

In this paper we approach the novel problem of segmenting an image based on a natural language expression. This is different from traditional semantic segmentation over a predefined set of semantic classes, as e.g., the …

Referring Expression SegmentationSegmentationSemantic Segmentation

Panoptic Narrative Grounding

2021-09-10 · C. González, N. Ayobi, I. Hernández, J. Hernández 외

This paper proposes Panoptic Narrative Grounding, a spatially fine and general formulation of the natural language visual grounding problem. We establish an experimental framework for the study of this new task, includin…

Natural Language Visual GroundingPanoptic SegmentationVisual Grounding

PhraseStereo: The First Open-Vocabulary Stereo Image Segmentation Dataset

2025-10-01 · Thomas Campagnolo, Ezio Malis, Philippe Martinet, Gaetan Bahl arxiv

Understanding how natural language phrases correspond to specific regions in images is a key challenge in multimodal semantic segmentation. Recent advances in phrase grounding are largely limited to single-view images, n…

Semantic SegmentationImage SegmentationPhrase Grounding

Panoptic Narrative Grounding

2021-01-01 · ICCV 2021 10 · Cristina Gonzalez, Nicolas Ayobi, Isabela Hernandez, Jose Hernandez 외

This paper proposes Panoptic Narrative Grounding, a spatially fine and general formulation of the natural language visual grounding problem. We establish an experimental framework for the study of this new task, incl…

Natural Language Visual GroundingPanoptic SegmentationVisual Grounding