Pith. sign in

REVIEW 4 cited by

A Recurrent Vision-and-Language BERT for Navigation

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 2011.13922 v2 pith:575MPIKY submitted 2020-11-26 cs.CV

classification cs.CV
keywords bertmodelnavigationrecurrentvision-and-languageapplicationdecisiontasks
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Accuracy of many visiolinguistic tasks has benefited significantly from the application of vision-and-language(V&L) BERT. However, its application for the task of vision-and-language navigation (VLN) remains limited. One reason for this is the difficulty adapting the BERT architecture to the partially observable Markov decision process present in VLN, requiring history-dependent attention and decision making. In this paper we propose a recurrent BERT model that is time-aware for use in VLN. Specifically, we equip the BERT model with a recurrent function that maintains cross-modal state information for the agent. Through extensive experiments on R2R and REVERIE we demonstrate that our model can replace more complex encoder-decoder models to achieve state-of-the-art results. Moreover, our approach can be generalised to other transformer-based architectures, supports pre-training, and is capable of solving navigation and referring expression tasks simultaneously.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. CAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models

    cs.RO 2025-08 conditional novelty 6.0 of 10

    Counterfactual language-action relabeling raises instruction-following success from about 26% to 53% in real-world navigation tests.

  2. Weakly-supervised VLM-guided Partial Contrastive Learning for Visual Language Navigation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A VLM-guided partial contrastive loss, which treats views sharing an object as positive pairs, improves visual language navigation success on R2R, REVERIE and SOON without VLM fine-tuning.

  3. World-Consistent Data Generation for Vision-and-Language Navigation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A 3D-guided data augmentation method generates world-consistent panoramic training data that improves a VLN agent's performance on unseen environments over prior augmentation baselines.

  4. Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation

    cs.CV 2025-04 conditional novelty 5.0 of 10

    MFRA combines a hierarchical DIRformer-style fusion backbone with instruction-guided attention and a GRU history encoder, reporting improved VLN benchmark scores.

Pith tools