SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.16997 · CVPR · 2024

Composed Video Retrieval via Enriched Context and Discriminative Embeddings

Mubarak Shah, Muzammal Naseer, Salman Khan, Rao Anwer, Fahad Shahbaz Khan, Michael Felsberg, Omkar Thawakar

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2403.16997.json · badge: /api/ran/2403.16997.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
omkarthawakar/composed-video-retrieval canonical (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
interpolate_pos_embed Ran
ran; our contract draft was wrong, not the code
omkarthawakar/composed-video-retrieval/src/model/vit.py
code served (permissive licence) · get_code("c6ec173f19f5c34d")
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) and returned Tensor, ndim 3, dtype family float, shape (1, 17, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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 PatchEmbed(nn.Module):
    def __init__(self, num_patches):
        super().__init__()
        self.num_patches = num_patches

class VisualEncoder(nn.Module):
    def __init__(self, num_patches, pos_embed_shape):
        super().__init__()
        self.patch_embed = PatchEmbed(num_patches)
        self.pos_embed = torch.randn(pos_embed_shape)

# Create a visual encoder with 16 patches (4x4 grid)
# pos_embed shape: (1, num_patches + num_extra_tokens, embedding_dim)
num_patches = 16
num_extra_tokens = 1
embedding_size = 4
visual_encoder = VisualEncoder(
    num_patches=num_patches,
    pos_embed_shape=(1, num_patches + num_extra_tokens, embedding_size)
)

# Create pos_embed_checkpoint with original size 2x2 (4 patches) + 1 extra token
# This will trigger interpolation from 2x2 to 4x4
orig_size = 2
orig_num_patches = orig_size * orig_size
pos_embed_checkpoint = torch.randn(1, orig_num_patches + num_extra_tokens, embedding_size)

ARGS = {
    "pos_embed_checkpoint": pos_embed_checkpoint,
    "visual_encoder": visual_encoder,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (1, 17, 4) — shape (1, 17, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 0 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.

FunctionAlso present inEarliest-datedOthers named
interpolate_pos_embed 52 other papers
32 dated earlier, 3 the same month, 15 later, 2 same year, order not determinable
1905.12794 (2019-05)
Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
2111.09452 (2021-11)
Open Vocabulary Object Detection with Pseudo Bounding-Box Labels
2205.11169 (2022-05)
PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
and 49 more not named here

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

Composed video retrieval (CoVR) is a challenging problem in computer vision which has recently highlighted the integration of modification text with visual queries for more sophisticated video search in large databases. Existing works predominantly rely on visual queries combined with modification text to distinguish relevant videos. However, such a strategy struggles to fully preserve the rich query-specific context in retrieved target videos and only represents the target video using visual embedding. We introduce a novel CoVR framework that leverages detailed language descriptions to explicitly encode query-specific contextual information and learns discriminative embeddings of vision only, text only and vision-text for better alignment to accurately retrieve matched target videos. Our proposed framework can be flexibly employed for both composed video (CoVR) and image (CoIR) retrieval tasks. Experiments on three datasets show that our approach obtains state-of-the-art performance for both CovR and zero-shot CoIR tasks, achieving gains as high as around 7% in terms of recall@K=1 score. Our code, detailed language descriptions for WebViD-CoVR dataset are available at https://github.com/ OmkarThawakar/composed-video-retrieval.

For agents

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

get_harvested_code_for_paper("2403.16997")
get_code_for_paper("2403.16997")
have("2403.16997")

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

curl https://syntology.ai/api/ran/2403.16997.json

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

[![Syntology run record](https://syntology.ai/api/ran/2403.16997.svg)](https://syntology.ai/paper/2403.16997)

Connect an agent — have() is free.