SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.02036 · ICCV · 2021

Anticipative Video Transformer

Kristen Grauman, Rohit Girdhar

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 2 have no contract verdict; 0 failures 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/2106.02036.json · badge: /api/ran/2106.02036.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
facebookresearch/AVT marked official in Papers with Code
Papers with Code archive
2 ran · 0 no recorded run
FunctionStatusWhere it lives
AVTh Ran
ran on a synthesized input
facebookresearch/AVT/models/future_prediction.py
code served (permissive licence) · get_code("6fce32ed337a95ea")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned tuple. 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
import transformers
import tempfile
import os

# Create a temporary centroids file for KmeansAssigner
temp_dir = tempfile.mkdtemp()
centroids_fpath = os.path.join(temp_dir, "centroids.pt")

# Create fake centroids: num_cluster_centers x feature_dim
num_cluster_centers = 50000
feature_dim = 8
centroids_data = {'weight': torch.randn(num_cluster_centers, feature_dim)}
torch.save(centroids_data, centroids_fpath)

INIT_ARGS = {
    'in_features': feature_dim,
    'output_len': 5,
    'output_len_eval': 5,
    'avg_last_n': -1,
    'inter_dim': 16,
    'future_pred_loss': None,
    'return_past_too': False,
    'drop_last_n': 0,
    'quantize_before_rollout': False,
    'assign_to_centroids': centroids_fpath,
    'num_cluster_centers': num_cluster_centers,
    'freeze_encoder_decoder': False,
    'n_layer': 2,
    'n_head': 2,
    'n_positions': 1024,
}

# feats: (B, T, C) where C matches feature_dim
# target_shape: (B, T', n_output)
batch_size = 2
seq_len = 3
output_seq_len = 5
n_output = 7

ARGS = {
    'feats': torch.randn(batch_size, seq_len, feature_dim),
    'target_shape': (batch_size, output_seq_len, n_output),
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
hydra, torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
KmeansAssigner Ran
ran on a synthesized input
facebookresearch/AVT/models/future_prediction.py
code served (permissive licence) · get_code("af9c1829ef2993e6")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, dtype family int, shape (2, 5) 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
import tempfile
import os

# Create a temporary centroids file
temp_dir = tempfile.mkdtemp()
centroids_fpath = os.path.join(temp_dir, 'centroids.pt')

# Create and save centroids: 3 clusters, 4-dimensional features
centroids = torch.randn(3, 4)
torch.save({'weight': centroids}, centroids_fpath)

INIT_ARGS = {
    'centroids_fpath': centroids_fpath,
    'norm': False,
}

# Test with float features: shape (2, 5, 4) means batch=2, seq=5, features=4
# This will be assigned to nearest cluster
ARGS = {
    'inp': torch.randn(2, 5, 4),
}

# Cleanup function
def cleanup():
    import shutil
    shutil.rmtree(temp_dir)

import atexit
atexit.register(cleanup)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 2, dtype family int, shape (2, 5) — shape (2, 5) 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

We propose Anticipative Video Transformer (AVT), an end-to-end attention-based video modeling architecture that attends to the previously observed video in order to anticipate future actions. We train the model jointly to predict the next action in a video sequence, while also learning frame feature encoders that are predictive of successive future frames' features. Compared to existing temporal aggregation strategies, AVT has the advantage of both maintaining the sequential progression of observed actions while still capturing long-range dependencies-both critical for the anticipation task. Through extensive experiments, we show that AVT obtains the best reported performance on four popular action anticipation benchmarks: EpicKitchens-55, EpicKitchens-100, EGTEA Gaze+, and 50-Salads; and it wins first place in the EpicKitchens-100 CVPR'21 challenge.

For agents

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

get_harvested_code_for_paper("2106.02036")
get_code_for_paper("2106.02036")
have("2106.02036")

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

curl https://syntology.ai/api/ran/2106.02036.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.02036.svg)](https://syntology.ai/paper/2106.02036)

Connect an agent — have() is free.