Pith. sign in

REVIEW 7 cited by

Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2004.00849 v2 pith:CYDYX5C6 submitted 2020-04-02 cs.CV cs.CLcs.LGcs.MM

Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers

classification cs.CV cs.CLcs.LGcs.MM
keywords languagevisualimagetasksmodelpixel-bertpixelsrepresentation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We propose Pixel-BERT to align image pixels with text by deep multi-modal transformers that jointly learn visual and language embedding in a unified end-to-end framework. We aim to build a more accurate and thorough connection between image pixels and language semantics directly from image and sentence pairs instead of using region-based image features as the most recent vision and language tasks. Our Pixel-BERT which aligns semantic connection in pixel and text level solves the limitation of task-specific visual representation for vision and language tasks. It also relieves the cost of bounding box annotations and overcomes the unbalance between semantic labels in visual task and language semantic. To provide a better representation for down-stream tasks, we pre-train a universal end-to-end model with image and sentence pairs from Visual Genome dataset and MS-COCO dataset. We propose to use a random pixel sampling mechanism to enhance the robustness of visual representation and to apply the Masked Language Model and Image-Text Matching as pre-training tasks. Extensive experiments on downstream tasks with our pre-trained model show that our approach makes the most state-of-the-arts in downstream tasks, including Visual Question Answering (VQA), image-text retrieval, Natural Language for Visual Reasoning for Real (NLVR). Particularly, we boost the performance of a single model in VQA task by 2.17 points compared with SOTA under fair comparison.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. HyFL-CLIP: Hyperbolic Fine-Tuning of CLIP for Robust Long-Context Understanding

    cs.CV 2026-07 unverdicted novelty 6.0

    HyFL-CLIP distills Euclidean CLIP alignment into hyperbolic space using cross-manifold similarity and Einstein midpoint aggregation to capture hierarchical part-whole relations, achieving up to 19.5% gains in long-tex...

  2. Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

    cs.CV 2025-01 conditional novelty 6.0

    Sa2VA unifies SAM-2 segmentation with MLLM reasoning into a single model for referring segmentation and conversation on images and videos, supported by a new 72k-expression Ref-SAV dataset.

  3. LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

    cs.CV 2023-10 unverdicted novelty 6.0

    LanguageBind aligns video, infrared, depth, and audio to a frozen language encoder via contrastive learning on the new VIDAL-10M dataset, extending video-language pretraining to N modalities.

  4. Kinky vortons in the 2HDM

    hep-ph 2026-03 conditional novelty 5.0

    Multiple dynamically stable kinky vortons exist in the Z2-symmetric global 2HDM and are accurately described by thin-string and elastic-string approximations.

  5. GIT: A Generative Image-to-text Transformer for Vision and Language

    cs.CV 2022-05 unverdicted novelty 5.0

    GIT achieves new state-of-the-art results on 12 vision-language benchmarks, including surpassing human performance on TextCaps, via a simplified single-encoder single-decoder transformer scaled on large pre-training data.

  6. Agent AI: Surveying the Horizons of Multimodal Interaction

    cs.AI 2024-01 unverdicted novelty 4.0

    The paper defines Agent AI as interactive multimodal systems that perceive grounded data and generate embodied actions, arguing this approach can mitigate hallucinations in foundation models.

  7. The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)

    cs.CV 2023-09 conditional novelty 4.0

    GPT-4V processes interleaved image-text inputs generically and supports visual referring prompting for new human-AI interaction.