AI Paper Atlas

Research map / Video / Video-language understanding

Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning

Zeyu Xi, Haoying Sun, Yaofei Wu, Junchi Yan, Haoran Zhang, Lifang Wu, Liang Wang, Changwen Chen

ICCV 2025 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the player identification network (PIN) to the LLM captioner (ablation)LLM-IAVC (Llama3.2-3B) · NBA-IdentityCIDEr: 66.5 -> 95.1Improved
add visual context learning module (VCLM) alone (ablation)LLM-IAVC (Llama3.2-3B) · NBA-IdentityCIDEr: 66.5 -> 66.8No clear effect
add VCLM on top of PIN (ablation)LLM-IAVC (Llama3.2-3B) · NBA-IdentityCIDEr: 95.1 -> 99.7Improved
add bidirectional semantic interaction module (BSIM) on top of PIN (ablation)LLM-IAVC (Llama3.2-3B) · NBA-IdentityCIDEr: 95.1 -> 103.4Improved
add VCLM when PIN and BSIM are present (ablation)LLM-IAVC (Llama3.2-3B) · NBA-IdentityCIDEr: 103.4 -> 105.3Improved
output both enhanced video and player features from BSIM instead of one (ablation)LLM-IAVC (Llama3.2-3B) · NBA-IdentityCIDEr: 101.7 / 102.3 -> 105.3Improved
add multimodal identity prompt to LLM decoder (ablation)LLM-IAVC (Llama3.2-3B) · NBA-IdentityCIDEr: 66.5 -> 105.3Improved
increase BSIM down-projection dimension from 512 to 768 (ablation)LLM-IAVC (Llama3.2-3B) · NBA-IdentityBLEU-4: 18.8 -> 18.0Hurt
reduce BSIM down-projection dimension from 512 to 128 (ablation)LLM-IAVC (Llama3.2-3B) · NBA-IdentityCIDEr: 105.3 -> 99.6Hurt
use TimeSformer instead of ResNet-50 as player identification backbone (ablation)Player identification network · NBA-Identity player classificationMCA: 90.12% -> 91.40%Improved
use C3D or I3D instead of image backbones for player identification (ablation)Player identification network · NBA-Identity player classificationMCA: C3D 50.86%, I3D 60.24% vs TimeSformer 91.40%Hurt
use Llama3.2-3B decoder instead of Qwen2.5-3B or GPT-2 (ablation)LLM-IAVC with prompt · NBA-IdentityCIDEr: 103.5 (Q-3B), 94.1 (GPT-2) -> 105.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy