<video>
The accident occurs at approximately 3.70 seconds in this clip.
Locate the center point of the accident region at this moment.
Use coordinates where [0,0] is the top-left corner and [1000,1000] is the bottom-right corner of the image.
Output JSON only with key: accident_center.

Expected output:

{"accident_center":[523,417]}

Inference example

bash

export IMAGE_MAX_TOKEN_NUM=1024
export VIDEO_MAX_TOKEN_NUM=1024
export FPS_MAX_FRAMES=48
export FPS=4
export FORCE_QWENVL_VIDEO_READER=torchcodec

swift infer \
  --model Qwen/Qwen3-VL-8B-Instruct \
  --adapters yzk9/accident-vlm-s8c-stageb-qwen3vl8b-lora \
  --val_dataset path/to/spatial_infer.jsonl \
  --max_new_tokens 64 \
  --temperature 0 \
  --result_path spatial_results.jsonl

Notes

This repository only contains the LoRA adapter weights, not the base model weights.
The adapter is intended for ACCIDENT-style traffic accident video understanding.
The model expects an accident time condition in the prompt.
For oracle-time evaluation, the accident time comes from ground-truth annotation.
For end-to-end evaluation, the accident time can be provided by a temporal grounding model such as T8-SAPO.
The output should be parsed as JSON and evaluated in relative_1000_xy coordinates.

Training summary

This adapter corresponds to the S8c Stage B spatial grounding model.

Input: local accident clip with accident time condition
Output: accident center point
Initialization: continued from the previous spatial clip model
Additional training: type-aware auxiliary continuation
Video token setting: VIDEO_MAX_TOKEN_NUM=1024
Frame setting: FPS=4, FPS_MAX_FRAMES=48

yzk9/accident-vlm-s8c-qwen3vl8b-lora

Accident-VLM S8c Qwen3-VL-8B LoRA Adapter

Model

Task description

Example prompt

Inference example

Notes

Training summary

yzk9/
accident-vlm-s8c-qwen3vl8b-lora