SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.09356 · ICCV · 2023

OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation

Xiangyu Zhang, Yuang Zhang, Tiancai Wang, Jianbing Shen, Dongming Wu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
wudongming97/onlinerefer canonical 6 of 7
FunctionStatusWhere it lives
aligned_bilinear Ran wudongming97/onlinerefer/models/onlinerefer.py
code served (permissive licence) · get_code("29dbbaafa4be18e1")
box_cxcywh_to_xyxy Ran wudongming97/onlinerefer/inference_davis_online.py
code served (permissive licence) · get_code("ef1a3e10a9dbf4a9")
compute_locations Ran wudongming97/onlinerefer/models/onlinerefer.py
code served (permissive licence) · get_code("ed1a308adb65f645")
parse_dynamic_params Ran wudongming97/onlinerefer/models/onlinerefer.py
code served (permissive licence) · get_code("46f34dc9f9a94b67")
pos2posemb Ran wudongming97/onlinerefer/models/deformable_transformer_plus.py
code served (permissive licence) · get_code("79016404390adaca")
rescale_bboxes Ran wudongming97/onlinerefer/inference_davis_online.py
code served (permissive licence) · get_code("2626a807bce7587a")
vis_add_mask Not yet run wudongming97/onlinerefer/inference_davis_online.py
code served (permissive licence) · get_code("ccbe959ea69981ad")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Referring video object segmentation (RVOS) aims at segmenting an object in a video following human instruction. Current state-of-the-art methods fall into an offline pattern, in which each clip independently interacts with text embedding for cross-modal understanding. They usually present that the offline pattern is necessary for RVOS, yet model limited temporal association within each clip. In this work, we break up the previous offline belief and propose a simple yet effective online model using explicit query propagation, named OnlineRefer. Specifically, our approach leverages target cues that gather semantic information and position prior to improve the accuracy and ease of referring predictions for the current frame. Furthermore, we generalize our online model into a semi-online framework to be compatible with video-based backbones. To show the effectiveness of our method, we evaluate it on four benchmarks, i.e.,

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2307.09356")
get_code_for_paper("2307.09356")
have("2307.09356")

Connect an agent — have() is free.