SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.12218 · IJCAI · 2023

Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment

Hao Li, Chang Liu, Jie Chen, Li Yuan, Jin Peng, Jinfa Huang, Zesen Cheng, Zhennan Wang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 23 functions out of this paper's own repositories and ran 9 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
jpthu17/DiCoSA canonical 7 of 16
jpthu17/diffusionret canonical 1 of 4
jpthu17/HBI — 1 of 3
FunctionStatusWhere it lives
swish Ran jpthu17/DiCoSA/tvr/models/until_module.py
code served (permissive licence) · get_code("0f786c407fb1ee4c")
basic_clean Ran jpthu17/DiCoSA/tvr/models/tokenization_clip.py
code served (permissive licence) · get_code("98f385d847636a3e")
euclidean_dist Ran jpthu17/DiCoSA/tvr/models/until_module.py
code served (permissive licence) · get_code("e54804982d1e6d22")
gelu Ran jpthu17/DiCoSA/tvr/models/until_module.py
code served (permissive licence) · get_code("50e1ffed03f484ec")
get_pairs Ran jpthu17/DiCoSA/tvr/models/tokenization_clip.py
code served (permissive licence) · get_code("d919ae32e5e4e616")
merge_tokens Ran jpthu17/HBI/HBI/models/cluster.py
code served (permissive licence) · get_code("0e49170b7c8f60fd")
url_to_filename Ran jpthu17/diffusionret/DiffusionRet/models/file_utils.py
code served (permissive licence) · get_code("af64ec220e8bcdbc")
warmup_linear Ran jpthu17/DiCoSA/tvr/models/optimization.py
code served (permissive licence) · get_code("e0960afdb0d64aa7")
whitespace_clean Ran jpthu17/DiCoSA/tvr/models/tokenization_clip.py
code served (permissive licence) · get_code("9542161e9640b858")
CTM Not yet run jpthu17/HBI/HBI/models/cluster.py
code served (permissive licence) · get_code("8bc3e8d24dc52e8b")
TokenConv Not yet run jpthu17/HBI/HBI/models/cluster.py
code served (permissive licence) · get_code("8b50e3e4f063bce8")
cached_path Not yet run jpthu17/diffusionret/DiffusionRet/models/file_utils.py
code served (permissive licence) · get_code("349d780dd4a89a37")
dataloader_activity_train Not yet run jpthu17/diffusionret/DiffusionRet/dataloaders/data_dataloaders.py
code served (permissive licence) · get_code("ab028ff1220c10c1")
dataloader_msrvtt_test Not yet run jpthu17/DiCoSA/tvr/dataloaders/data_dataloaders.py
code served (permissive licence) · get_code("b6070984a76e9bf3")
dataloader_msrvtt_train Not yet run jpthu17/DiCoSA/tvr/dataloaders/data_dataloaders.py
code served (permissive licence) · get_code("780f499e676f8267")
dataloader_msrvtt_train_test Not yet run jpthu17/DiCoSA/tvr/dataloaders/data_dataloaders.py
code served (permissive licence) · get_code("70d56cc28b0d7a14")
filename_to_url Not yet run jpthu17/diffusionret/DiffusionRet/models/file_utils.py
code served (permissive licence) · get_code("db0ac56aaf6e35e6")
get_args Not yet run jpthu17/DiCoSA/main_retrieval.py
code served (permissive licence) · get_code("91e7fe98724c5bad")
load_stopwords Not yet run jpthu17/DiCoSA/tvr/dataloaders/dataloader_activitynet_retrieval.py
code served (permissive licence) · get_code("d227e7f9a9ea755e")
remove_stopwords Not yet run jpthu17/DiCoSA/tvr/dataloaders/dataloader_activitynet_retrieval.py
code served (permissive licence) · get_code("1d11677b554a969d")
set_seed_logger Not yet run jpthu17/DiCoSA/main_retrieval.py
code served (permissive licence) · get_code("8952edef143f2747")
warmup_constant Not yet run jpthu17/DiCoSA/tvr/models/optimization.py
code served (permissive licence) · get_code("59e4e730a9dc5dc6")
warmup_cosine Not yet run jpthu17/DiCoSA/tvr/models/optimization.py
code served (permissive licence) · get_code("20b3d25ba1b796e5")

Repositories linked to this paper

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

Abstract

Text-video retrieval is a challenging cross-modal task, which aims to align visual entities with natural language descriptions. Current methods either fail to leverage the local details or are computationally expensive. What's worse, they fail to leverage the heterogeneous concepts in data. In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings. For disentangled conceptualization, we divide the coarse feature into multiple latent factors related to semantic concepts. For set-to-set alignment, where a set of visual concepts correspond to a set of textual concepts, we propose an adaptive pooling method to aggregate semantic concepts to address partial matching. In particular, since we encode concepts independently in only a few dimensions, DiCoSA is superior at efficiency and granularity, ensuring fine-grained interactions using a similar computational complexity as coarse-grained alignment. Extensive experiments on five datasets, including MSR-VTT, LSMDC, MSVD, ActivityNet, and DiDeMo, demonstrate that our method outperforms the existing state-of-the-art methods.

For agents

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

get_harvested_code_for_paper("2305.12218")
get_code_for_paper("2305.12218")
have("2305.12218")

Connect an agent — have() is free.