Xiangyu Zhang, Yuang Zhang, Tiancai Wang, Jianbing Shen, Dongming Wu
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.
| Repository | Role | Ran |
|---|---|---|
| wudongming97/onlinerefer | canonical | 6 of 7 |
| Function | Status | Where 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") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.,
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.