mlsanityData to 7 Oct 2026

A Better Variant of Self-Critical Sequence Training

arXiv 2003.09971 ↗First posted 22 Mar 2020cs.CV cs.CLcited by 23

Not on the map. Why?

Abstract (arXiv)

In this work, we present a simple yet better variant of Self-Critical Sequence Training. We make a simple change in the choice of baseline function in REINFORCE algorithm. The new baseline can bring better performance with no extra cost, compared to the greedy decoding baseline.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 10; 2023: 4; 2024: 1; 2025: 1.

23 papers.

Sort:

  1. 2021How Much Can CLIP Benefit Vision-and-Language Tasks?cited by 321
  2. 2022Fine-grained Image Captioning with CLIP Rewardcited by 69
  3. 2022NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Taskscited by 60
  4. 2022Comprehending and Ordering Semantics for Image Captioningcited by 33
  5. 2025AVD2: Accident Video Diffusion for Accident Video Descriptioncited by 20
  6. 2022Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioningcited by 18
  7. 2021ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Modelscited by 16
  8. 2021Reinforcement Learning-powered Semantic Communication via Semantic Similaritycited by 15
  9. 2021Semi-Autoregressive Transformer for Image Captioningcited by 12
  10. 2021Transcribing Natural Languages for The Deaf via Neural Editing Programscited by 7
  11. 2022Image Captioning via Compact Bidirectional Architecturecited by 7
  12. 2022ACORT: A Compact Object Relation Transformer for Parameter Efficient Image Captioningcited by 6
11 more
  1. 2022When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensitycited by 5
  2. 2023Generating Context-Aware Natural Answers for Questions in 3D Scenescited by 5
  3. 2021End-to-End Supermask Pruning: Learning to Prune Image Captioning Modelscited by 2
  4. 2022Exploring the sequence length bottleneck in the Transformer for Image Captioningcited by 2
  5. 2023A request for clarity over the End of Sequence token in the Self-Critical Sequence Trainingcited by 2
  6. 2021Goal-driven text descriptions for imagescited by 1
  7. 2022Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learningcited by 1
  8. 2023Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioningcited by 1
  9. 2023Bounding and Filling: A Fast and Flexible Framework for Image Captioningcited by 1
  10. 2024Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translationcited by 1
  11. 2022Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioningcited by 0