Methods › Computer Vision › Vision and Language Pre-Trained Models › LXMERT
Learning Cross-Modality Encoder Representations from Transformers
LXMERT
Introduced by Hao Tan et al. in LXMERT: Learning Cross-Modality Encoder Representations from Transformers
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
LXMERT is a model for learning vision-and-language cross-modality representations. It consists of a Transformer model that consists three encoders: object relationship encoder, a language encoder, and a cross-modality encoder. The model takes two inputs: image with its related sentence. The images are represented as a sequence of objects, whereas each sentence is represented as sequence of words. By combining the self-attention and cross-attention layers the model is able to generated language representation, image representations, and cross-modality representations from the input. The model is pre-trained with image-sentence pairs via five pre-training tasks: masked language modeling, masked object prediction, cross-modality matching, and image questions answering. These tasks help the model to learn both intra-modality and cross-modality relationships.
In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 9 in the graph, strongest link: official). This answer is about arXiv:1908.07490, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1908.07490 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (of 15 harvested samples) · 3 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 40 · with a code link: 17 · where Syntology ran a sample: 7 (7 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (7 of 40 tagged: 7 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 40 of 40, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Optimizing Visual Question Answering Models for Driving: Bridging the Gap Between Human and Machine Attention Patterns 13 Jun 2024 · 0 repositories · arXiv:2406.09203
-
Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking 29 Jan 2024 · 1 repository · arXiv:2401.16575
-
LXMERT Model Compression for Visual Question Answering 23 Oct 2023 · 2 repositories · arXiv:2310.15325
-
Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models 18 Aug 2023 · 0 repositories · arXiv:2308.09778
-
Towards a performance analysis on pre-trained Visual Question Answering models for autonomous driving 18 Jul 2023 · 1 repository · arXiv:2307.09329
-
An Empirical Study on the Language Modal in Visual Question Answering 17 May 2023 · 0 repositories · arXiv:2305.10143
-
Probing the Role of Positional Information in Vision-Language Models 17 May 2023 · 0 repositories · arXiv:2305.10046
-
Controlling for Stereotypes in Multimodal Language Model Evaluation 3 Feb 2023 · 0 repositories · arXiv:2302.01582
-
MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks 15 Dec 2022 · 1 repository · arXiv:2212.08158Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 10 harvested samples)
-
Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference 21 Nov 2022 · 0 repositories · arXiv:2211.11875
-
Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering 26 Oct 2022 · 1 repository · arXiv:2210.14558
-
Probing Cross-modal Semantics Alignment Capability from the Textual Perspective 18 Oct 2022 · 0 repositories · arXiv:2210.09550
-
Generative Bias for Robust Visual Question Answering 1 Aug 2022 · 1 repository · arXiv:2208.00690Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations 1 Jul 2022 · 1 repository · arXiv:2207.00221
-
Visual Spatial Reasoning 30 Apr 2022 · 4 repositories · arXiv:2205.00363Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 6 pointer-only (licence)
-
Visio-Linguistic Brain Encoding 18 Apr 2022 · 0 repositories · arXiv:2204.08261
-
SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering 5 Apr 2022 · 1 repository · arXiv:2204.02285
-
Exploring Multi-Modal Representations for Ambiguity Detection & Coreference Resolution in the SIMMC 2.0 Challenge 25 Feb 2022 · 2 repositories · arXiv:2202.12645
-
Probing the Role of Positional Information in Vision-Language Models 16 Jan 2022 · 0 repositories
-
Multimodal Learning: Are Captions All You Need? 16 Nov 2021 · 0 repositories
-
Region under Discussion for visual dialog 1 Nov 2021 · 0 repositories
-
Seeing things or seeing scenes: Investigating the capabilities of V&L models to align scene descriptions to images 16 Oct 2021 · 0 repositories
-
Dense Contrastive Visual-Linguistic Pretraining 24 Sep 2021 · 0 repositories · arXiv:2109.11778
-
What Vision-Language Models `See' when they See Scenes 15 Sep 2021 · 0 repositories · arXiv:2109.07301
-
Data Efficient Masked Language Modeling for Vision and Language 5 Sep 2021 · 1 repository · arXiv:2109.02040
-
Learning to Read Maps: Understanding Natural Language Instructions from Unseen Maps 1 Aug 2021 · 1 repository
-
Multi-stage Pre-training over Simplified Multimodal Pre-training Models 22 Jul 2021 · 1 repository · arXiv:2107.14596Syntology official (archive's flag): 3 ran · 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 3 samples that ran constructed an object rather than computing a result (of 9 harvested samples) · 9 pointer-only (licence)
-
Passage Retrieval for Outside-Knowledge Visual Question Answering 9 May 2021 · 1 repository · arXiv:2105.03938Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads 30 Apr 2021 · 0 repositories · arXiv:2104.14741
-
Playing Lottery Tickets with Vision and Language 23 Apr 2021 · 0 repositories · arXiv:2104.11832
-
Analysis on Image Set Visual Question Answering 31 Mar 2021 · 0 repositories · arXiv:2104.00107
-
Visual Grounding Strategies for Text-Only Natural Language Processing 25 Mar 2021 · 0 repositories · arXiv:2103.13942
-
Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks 22 Dec 2020 · 0 repositories · arXiv:2012.12352
-
They Are Not All Alike: Answering Different Spatial Questions Requires Different Grounding Strategies 1 Nov 2020 · 0 repositories
-
X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers 23 Sep 2020 · 2 repositories · arXiv:2009.11278Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports 3 Sep 2020 · 1 repository · arXiv:2009.01523
-
Contrastive Visual-Linguistic Pretraining 26 Jul 2020 · 0 repositories · arXiv:2007.13135
-
What Does BERT with Vision Look At? 1 Jul 2020 · 0 repositories
-
Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models 15 May 2020 · 0 repositories · arXiv:2005.07310
-
LXMERT: Learning Cross-Modality Encoder Representations from Transformers 20 Aug 2019 · 9 repositories · arXiv:1908.07490Syntology community repositories only · 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified; every one of the 4 samples that ran constructed an object rather than computing a result (of 15 harvested samples) · 3 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 44 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections