SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.17534 · NeurIPS · 2024

OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking

Haiji Liang, Ruize Han

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 0 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
Coo1Sea/OVT-B-Dataset canonical 0 of 10
FunctionStatusWhere it lives
check_imports Not yet run Coo1Sea/OVT-B-Dataset/diffusers_clean/dynamic_modules_utils.py
code served (permissive licence) · get_code("301682fc3342590a")
compute_teta_on_ovsetup Not yet run Coo1Sea/OVT-B-Dataset/ovtrack/datasets/ovtb_dataset.py
code served (permissive licence) · get_code("ce381f589ee1973b")
convert_coco_result_to_bdd Not yet run Coo1Sea/OVT-B-Dataset/ovtrack/datasets/bdd_video_dataset.py
code served (permissive licence) · get_code("c4627f5ef95612d0")
convert_pred_to_label_format Not yet run Coo1Sea/OVT-B-Dataset/ovtrack/datasets/bdd_video_dataset.py
code served (permissive licence) · get_code("a8850d80988810a1")
get_parameter_device Not yet run Coo1Sea/OVT-B-Dataset/diffusers_clean/modeling_utils.py
code served (permissive licence) · get_code("6d9f63b783b9c061")
get_parameter_dtype Not yet run Coo1Sea/OVT-B-Dataset/diffusers_clean/modeling_utils.py
code served (permissive licence) · get_code("278603330ce5c616")
get_relative_import_files Not yet run Coo1Sea/OVT-B-Dataset/diffusers_clean/dynamic_modules_utils.py
code served (permissive licence) · get_code("00cc853a73f3aeb6")
get_relative_imports Not yet run Coo1Sea/OVT-B-Dataset/diffusers_clean/dynamic_modules_utils.py
code served (permissive licence) · get_code("450aeffe7f80f917")
load_state_dict Not yet run Coo1Sea/OVT-B-Dataset/diffusers_clean/modeling_utils.py
code served (permissive licence) · get_code("fa98be725f1850b4")
majority_vote Not yet run Coo1Sea/OVT-B-Dataset/ovtrack/datasets/bdd_video_dataset.py
code served (permissive licence) · get_code("d669627a4785e5e9")

Repositories linked to this paper

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

Abstract

Open-vocabulary object perception has become an important topic in artificial intelligence, which aims to identify objects with novel classes that have not been seen during training. Under this setting, open-vocabulary object detection (OVD) in a single image has been studied in many literature. However, open-vocabulary object tracking (OVT) from a video has been studied less, and one reason is the shortage of benchmarks. In this work, we have built a new large-scale benchmark for open-vocabulary multi-object tracking namely OVT-B. OVT-B contains 1,048 categories of objects and 1,973 videos with 637,608 bounding box annotations, which is much larger than the sole open-vocabulary tracking dataset, i.e., OV-TAO-val dataset (200+ categories, 900+ videos). The proposed OVT-B can be used as a new benchmark to pave the way for OVT research. We also develop a simple yet effective baseline method for OVT. It integrates the motion features for object tracking, which is an important feature for MOT but is ignored in previous OVT methods. Experimental results have verified the usefulness of the proposed benchmark and the effectiveness of our method. We have released the benchmark to the public at https://github.com/Coo1Sea/OVT-B-Dataset.

For agents

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

get_harvested_code_for_paper("2410.17534")
get_code_for_paper("2410.17534")
have("2410.17534")

Connect an agent — have() is free.