SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.02439 · CVPR · 2021

Few-Shot Transformation of Common Actions into Time and Space

Cees Snoek, Pascal Mettes, Pengwan Yang

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (3 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 0 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2104.02439.json · badge: /api/ran/2104.02439.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
PengWan-Yang/few-shot-transformer community
Papers with Code archive
4 ran · 1 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
PengWan-Yang/few-shot-transformer/models/transformer.py
code served (permissive licence) · get_code("ead2dccc5b1e3c86")
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, BasicBlock: 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
import math

torch.manual_seed(0)

ARGS = {
    'in_channels': 4,
    'inter_channels': 2,
    'sub_sample': False,
    'bn_layer': True,
    'dropout': 0.2,
    'out_channels': 8,
}
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 BasicBlock — 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 BasicBlock 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
LayerNorm Ran
ran on a synthesized input · constructed an object; no result was computed
PengWan-Yang/few-shot-transformer/models/transformer.py
code served (permissive licence) · get_code("158e0dc0859577bd")
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, LayerNorm: 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
from torch import nn

torch.manual_seed(0)

# LayerNorm.__init__ takes only eps parameter
# LayerNorm.forward takes x (a tensor)
# The forward method calls:
#   - x.mean(-1, keepdim=True)
#   - x.std(-1, keepdim=True)
#   - arithmetic operations on tensors

# Create a small test tensor: batch_size=2, feature_dim=4
x = torch.randn(2, 4)

ARGS = {
    'eps': 1e-06
}
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 LayerNorm — 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 LayerNorm 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
TransformerDecoder Ran
ran on a synthesized input · constructed an object; no result was computed
PengWan-Yang/few-shot-transformer/models/transformer.py
code served (permissive licence) · get_code("762341b0c8db1cb3")
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, TransformerDecoder: 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)

# Define a minimal decoder layer that satisfies the forward signature
class MinimalDecoderLayer(nn.Module):
    def __init__(self, d_model=4):
        super().__init__()
        self.d_model = d_model
        self.linear = nn.Linear(d_model, d_model)
    
    def forward(self, tgt, memory, mem_support, shot, tgt_mask=None, memory_mask=None, 
                tgt_key_padding_mask=None, memory_key_padding_mask=None, pos=None, query_pos=None):
        # Minimal implementation that processes tgt and returns output of same shape
        return self.linear(tgt)

# Define a minimal norm layer
class MinimalNorm(nn.Module):
    def __init__(self, d_model=4):
        super().__init__()
        self.d_model = d_model
    
    def forward(self, x):
        return x / (x.norm(dim=-1, keepdim=True) + 1e-8)

# Create parameters
d_model = 4
batch_size = 2
seq_len = 3
num_layers = 2

decoder_layer = MinimalDecoderLayer(d_model=d_model)
norm = MinimalNorm(d_model=d_model)

tgt = torch.randn(seq_len, batch_size, d_model)
memory = torch.randn(5, batch_size, d_model)
mem_support = torch.randn(6, batch_size, d_model)
shot = torch.randn(4, batch_size, d_model)

ARGS = {
    "decoder_layer": decoder_layer,
    "num_layers": num_layers,
    "norm": norm,
    "return_intermediate": False,
}
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 TransformerDecoder — 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 TransformerDecoder 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
TransformerDecoderLayer Ran
ran on a synthesized input
PengWan-Yang/few-shot-transformer/models/transformer.py
code served (permissive licence) · get_code("2ea7d8af7a370ee2")
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 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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, Tensor

INIT_ARGS = {
    'd_model': 4,
    'nhead': 2,
    'dim_feedforward': 8,
    'dropout': 0.1,
    'activation': 'relu',
    'normalize_before': False,
    'shot': 1
}

# Create small tensors for the forward call
batch_size = 2
seq_len = 3
support_size = 5
d_model = INIT_ARGS['d_model']

# tgt: (seq_len, batch_size, d_model)
tgt = torch.randn(seq_len, batch_size, d_model)

# memory: (seq_len, batch_size, d_model)
memory = torch.randn(seq_len, batch_size, d_model)

# mem_support: (support_size, d_model) - used in mutual_attn
mem_support = torch.randn(support_size, d_model)

# Optional positional embeddings
pos = torch.randn(seq_len, 1, d_model)  # (seq_len, 1, d_model) for broadcasting
query_pos = torch.randn(seq_len, batch_size, d_model)

ARGS = {
    'tgt': tgt,
    'memory': memory,
    'mem_support': mem_support,
    'shot': INIT_ARGS['shot'],
    'pos': pos,
    'query_pos': query_pos
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy, 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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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)
Transformer Not yet run
unverified (harvested, no recorded run)
PengWan-Yang/few-shot-transformer/models/transformer.py
code served (permissive licence) · get_code("8c58e4a15c842b0e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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 2026-11-21.

Repositories linked to this paper

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

Abstract

This paper introduces the task of few-shot common action localization in time and space. Given a few trimmed support videos containing the same but unknown action, we strive for spatio-temporal localization of that action in a long untrimmed query video. We do not require any class labels, interval bounds, or bounding boxes. To address this challenging task, we introduce a novel few-shot transformer architecture with a dedicated encoder-decoder structure optimized for joint commonality learning and localization prediction, without the need for proposals. Experiments on reorganizations of the AVA and UCF101-24 datasets show the effectiveness of our approach for few-shot common action localization, even when the support videos are noisy. Although we are not specifically designed for common localization in time only, we also compare favorably against the fewshot and one-shot state-of-the-art in this setting. Lastly, we demonstrate that the few-shot transformer is easily extended to common action localization per pixel.

For agents

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

get_harvested_code_for_paper("2104.02439")
get_code_for_paper("2104.02439")
have("2104.02439")

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

curl https://syntology.ai/api/ran/2104.02439.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.02439.svg)](https://syntology.ai/paper/2104.02439)

Connect an agent — have() is free.