SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.16702 · ICLR · 2024

Multi-granularity Correspondence Learning from Long-term Noisy Videos

Jia Liu, Jie Zhang, Xi Peng, Yijie Lin, Zhenyu Huang, Zujie Wen

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2401.16702.json · badge: /api/ran/2401.16702.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
XLearning-SCU/2024-ICLR-Norton community
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
Loss Ran
ran on a synthesized input · constructed an object; no result was computed
XLearning-SCU/2024-ICLR-Norton/mmpt/losses/nce.py
code served (permissive licence) · get_code("3c604915121f5194")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, Loss: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

class Loss(object):

    def __call__(self, *args, **kwargs):
        raise NotImplementedError


ARGS = {}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Loss — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Loss output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
SequenceContrastLoss Ran
ran on a synthesized input · constructed an object; no result was computed
XLearning-SCU/2024-ICLR-Norton/mmpt/losses/nce.py
code served (permissive licence) · get_code("fa8f4f2b0da67ea8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, SequenceContrastLoss: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from torch import nn


class Config:
    """Stand-in config object with nested attributes"""
    def __init__(self):
        self.loss = type('obj', (object,), {})()
        self.loss.sequence_contrast = type('obj', (object,), {})()
        self.loss.sequence_contrast.threshold = 2  # length
        self.loss.sequence_contrast.scale = 0.1
        self.loss.sequence_contrast.prompt_ratio = 0.5
        self.loss.alpha_lse = 10.0
        self.loss.fusion_weight = 0.5
        self.loss.sinkhorn_iterations = 5
        self.dataset = type('obj', (object,), {})()
        self.dataset.clip_per_video = 8  # must be divisible by threshold


torch.manual_seed(0)

config = Config()

# Create loss instance
loss_fn = nn.CrossEntropyLoss()

# Create tensors for __call__ method
batch_size = 4
feature_dim = 16
text_length = 3
video_length = 2

# pooled_video and pooled_text: (batch_size, feature_dim)
pooled_video = torch.randn(batch_size, feature_dim)
pooled_text = torch.randn(batch_size, feature_dim)

# video_outputs: (batch, video_clips, feature_dim)
video_outputs = torch.randn(batch_size, video_length, feature_dim)

# text_outputs: (batch, text_tokens, feature_dim)
text_outputs = torch.randn(batch_size, text_length, feature_dim)

# video_mask_outputs: (batch, video_clips)
video_mask_outputs = torch.ones(batch_size, video_length)

# text_mask_outputs: (batch, text_tokens)
text_mask_outputs = torch.ones(batch_size, text_length)

kwargs = {
    'video_outputs': video_outputs,
    'text_outputs': text_outputs,
    'video_mask_outputs': video_mask_outputs,
    'text_mask_outputs': text_mask_outputs,
}

ARGS = {
    'config': config,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SequenceContrastLoss — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SequenceContrastLoss output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
MMContraLoss Not yet run
unverified (harvested, no recorded run)
XLearning-SCU/2024-ICLR-Norton/mmpt/losses/nce.py
code served (permissive licence) · get_code("14142a69635283c4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

Existing video-language studies mainly focus on learning short video clips, leaving long-term temporal dependencies rarely explored due to over-high computational cost of modeling long videos. To address this issue, one feasible solution is learning the correspondence between video clips and captions, which however inevitably encounters the multi-granularity noisy correspondence (MNC) problem. To be specific, MNC refers to the clip-caption misalignment (coarse-grained) and frame-word misalignment (fine-grained), hindering temporal learning and video understanding. In this paper, we propose NOise Robust Temporal Optimal traNsport (Norton) that addresses MNC in a unified optimal transport (OT) framework. In brief, Norton employs video-paragraph and clip-caption contrastive losses to capture long-term dependencies based on OT. To address coarse-grained misalignment in video-paragraph contrast, Norton filters out the irrelevant clips and captions through an alignable prompt bucket and realigns asynchronous clip-caption pairs based on transport distance. To address the fine-grained misalignment, Norton incorporates a soft-maximum operator to identify crucial words and key frames. Additionally, Norton exploits the potential faulty negative samples in clipcaption contrast by rectifying the alignment target with OT assignment to ensure precise temporal modeling. Extensive experiments on video retrieval, videoQA, and action segmentation verify the effectiveness of our method. Code is available at https://lin-yijie.github.io/projects/Norton.

For agents

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

get_harvested_code_for_paper("2401.16702")
get_code_for_paper("2401.16702")
have("2401.16702")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2401.16702.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2401.16702.svg)](https://syntology.ai/paper/2401.16702)

Connect an agent — have() is free.