Challenge: Existing video captioning models fail to capture nuanced semantics of videos . existing models generate coarse descriptions of human motions, resulting in poor quality .
Approach: They construct a fine-grained human motion video captioning dataset named BoFiT and a model that generates fine-grain descriptions of human motions via prompting.
Outcome: The proposed model outperforms existing models on comprehensive metrics.

Similar Papers

Motion Generation from Fine-grained Textual Descriptions (2024.lrec-main)

Copied to clipboard

Challenge: Existing models for motion generation from textual descriptions are limited to coarse-grained descriptions.
Approach: They build a large-scale language-motion dataset specializing in fine-grained textual descriptions . they feed it with step-by-step instructions with pseudo-code compulsory checks . quantitative evaluation shows that the model outperforms MotionDiffuse in generating spatially or chronologically composite motions .
Outcome: The proposed model outperforms existing models in generating human motion sequences from textual descriptions by a large margin.
Diving Deep into the Motion Representation of Video-Text Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing video-text models that capture motion in videos are lacking in quality.
Approach: They propose a method to improve motion understanding in video-text models by utilizing motion descriptions to capture motion in action videos.
Outcome: The proposed pipeline improves motion understanding on two action datasets and shows that it is effective on fine-grained motion descriptions.
HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing studies have shown that high-quality video captions can improve MLLMs' performance on videos involving human actions.
Approach: They propose a data annotation pipeline to collect videos featuring clear human actions from the Internet and annotate them in a standardized caption format that uses human attributes to distinguish individuals.
Outcome: The proposed pipeline combines two datasets to evaluate human action understanding.
Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease.
Approach: They propose to use a multiple granularity attribute-centric benchmark and training mixture to evaluate LVLMs’ fine-grained visual comprehension ability.
Outcome: The proposed model improves on LLaVa-1.5, InstructBLIP and GPT-4V and demonstrates that they struggle to generate descriptive visual attributes based on a concept that appears within an input image despite their prominent zero-shot image captioning ability.
YouMakeup: A Large-Scale Domain-Specific Multimodal Dataset for Fine-Grained Semantic Comprehension (D19-1)

Copied to clipboard

Challenge: Multimodal semantic comprehension has attracted increasing research interest recently such as visual question answering and caption generation.
Approach: They propose to use a large-scale multimodal instructional video dataset to support fine-grained comprehension research in specific domain.
Outcome: The proposed dataset contains 2,800 videos from YouTube, spanning more than 420 hours in total.
Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training (2026.acl-long)

Copied to clipboard

Challenge: Existing models for fine-grained speaking styles are limited in terms of accuracy, coverage, and naturalness.
Approach: They propose a model that pre-trains with coarse captions and annotates with a pipeline that grounds captions in audio.
Outcome: The proposed model outperforms existing models with fine-grained style annotations . it integrates global and fine-granular supervision, enabling unified representations based on the proposed model .
GenProve: Learning to Generate Text with Fine-Grained Provenance (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for large language models (LLMs) are coarse-grained and fail to distinguish between direct quotes and complex reasoning.
Approach: They propose a framework that combines supervised fine-tuning and group relative policy optimization to generate fluent answers while simultaneously producing sentence-level provenance triples.
Outcome: The proposed framework outperforms 14 strong large language models in joint evaluation.
Multimodal Pretraining for Dense Video Captioning (2020.aacl-main)

Copied to clipboard

Challenge: a billion hours of videos are being watched on YouTube every day . videos are difficult to skim through, making it harder to quickly target the relevant part(s) of a video.
Approach: They propose to use a video timeline tag dataset to generate time-stamped annotations for videos . they propose to pretrain and finetune captioning models using YouCook2 and ViTT .
Outcome: The proposed model generalizes well and is robust over a wide variety of instructional videos.
How Much Do Large Language Models Know about Human Motion? A Case Study in 3D Avatar Control (2025.findings-emnlp)

Copied to clipboard

Challenge: a new study explores the human motion knowledge of Large Language Models (LLMs) using 3D avatar control.
Approach: They use 20 representative motion instructions to interpolate LLMs into avatar animations . they find they are strong at interpreting high-level body movements but struggle with precise body part positioning .
Outcome: The proposed model is strong at interpreting high-level body movements but struggles with precise body part positioning.
Video Caption Dataset for Describing Human Actions in Japanese (2020.lrec-1)

Copied to clipboard

Challenge: Existing video caption datasets for English have no equivalent for Japanese . authors evaluated two methods to obtain benchmark results .
Approach: They propose to use Japanese video captions to describe human actions . they evaluated two different methods to obtain benchmark results .
Outcome: The proposed dataset evaluates two different methods to obtain benchmark results . it shows that the generation methods can specify "who does what and where"

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations