Pith. sign in

REVIEW 9 cited by

VideoBERT: A Joint Model for Video and Language Representation Learning

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 1904.01766 v2 pith:4Q7IAPHI submitted 2019-04-03 cs.CV cs.AI

classification cs.CVcs.AI
keywords modelvideodatajointlearncaptioningclassificationfeatures
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. In particular, inspired by its recent success in language modeling, we build upon the BERT model to learn bidirectional joint distributions over sequences of visual and linguistic tokens, derived from vector quantization of video data and off-the-shelf speech recognition outputs, respectively. We use VideoBERT in numerous tasks, including action classification and video captioning. We show that it can be applied directly to open-vocabulary classification, and confirm that large amounts of training data and cross-modal information are critical to performance. Furthermore, we outperform the state-of-the-art on video captioning, and quantitative results verify that the model learns high-level semantic features.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

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

  1. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks

    cs.CV 2019-08 conditional novelty 8.0 of 10

    A two-stream BERT-style model pretrained on weakly aligned image-caption data transfers to VQA, VCR, referring expressions, and retrieval, outperforming task-specific models on all four.

  2. LXMERT: Learning Cross-Modality Encoder Representations from Transformers

    cs.CL 2019-08 accept novelty 7.0 of 10

    LXMERT pretrains a three-encoder Transformer on image-sentence pairs with five tasks and achieves state-of-the-art VQA, GQA, and NLVR2 results after fine-tuning.

  3. Fusion of Detected Objects in Text for Visual Question Answering

    cs.CL 2019-08 conditional novelty 7.0 of 10

    Injecting detected object features into BERT's token embeddings (early fusion) improved visual question answering and achieved state-of-the-art results on VCR.

  4. CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models

    cs.CV 2026-08 conditional novelty 6.0 of 10

    CLIP-CC-Bench is a 200-clip benchmark with expert paragraph references that ranks 17 video-language models via an ensemble of five embedding-based semantic judges.

  5. AdaCM$^2$: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction

    cs.CV 2024-11 conditional novelty 6.0 of 10

    AdaCM2 adaptively evicts low-attention video tokens using cross-modality attention scores, keeping memory bounded while improving accuracy on long-video QA, captioning, and classification.

  6. VL-BERT: Pre-training of Generic Visual-Linguistic Representations

    cs.CV 2019-08 accept novelty 6.0 of 10

    VL-BERT pre-trains a single-stream Transformer on image captions and text, and the resulting representation improves VCR, VQA, and RefCOCO+ benchmarks.

  7. Integrating Multimodal Information in Large Pretrained Transformers

    cs.LG 2019-08 conditional novelty 6.0 of 10

    The Multimodal Adaptation Gate lets BERT and XLNet be fine-tuned with visual and acoustic inputs, improving multimodal sentiment analysis and reaching human-level scores on CMU-MOSI.

  8. Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training

    cs.CV 2019-08 conditional novelty 4.0 of 10

    Image-caption pre-training with masked language, masked object, and image-text matching objectives improves image-text retrieval and, to a lesser extent, visual commonsense reasoning.

  9. The Quest for Visual Understanding: A Journey Through the Evolution of Visual Question Answering

    cs.CV 2025-01 reject novelty 2.0 of 10

    A survey tracing the evolution of visual question answering from 2015 CNN-LSTM models through attention mechanisms, modular networks, vision-language pretraining, and large multimodal models.

Pith tools