SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.13611 · ICCV · 2021

Class-Incremental Learning for Action Recognition in Videos

Minsoo Kang, Bohyung Han, Jaeyoo Park

arXiv · PDF · Open in the Atlas

Code that ran

6 of 11 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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 5 no recorded run), measured 2026-11-22; 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/2203.13611.json · badge: /api/ran/2203.13611.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
mit-han-lab/temporal-shift-module canonical (classifier label)
classifier basis not recorded on the link
6 ran · 5 no recorded run
FunctionStatusWhere it lives
conv_1x1_bn Ran
ran; our contract draft was wrong, not the code
mit-han-lab/temporal-shift-module/archs/mobilenet_v2.py
pointer only (licence: MIT); the stored copy get_code serves, from zhoudaquan/rethinking_bottleneck_design, is pointer only (licence: NOASSERTION) · get_code("a0131fb70c267a9e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from zhoudaquan/rethinking_bottleneck_design, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

conv_bn Ran
ran; our contract draft was wrong, not the code
mit-han-lab/temporal-shift-module/archs/mobilenet_v2.py
code served (permissive licence) · get_code("e087cbfa1e53486d")
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 Sequential. 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)

ARGS = {
    "inp": 3,
    "oup": 16,
    "stride": 1
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
make_divisible Ran
ran, honoured the contract we drafted
mit-han-lab/temporal-shift-module/archs/mobilenet_v2.py
pointer only (licence: MIT); the stored copy get_code serves, from chris-boson/fashion_mnist, is pointer only (licence: NONE) · get_code("63ec083689f80f47")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from chris-boson/fashion_mnist, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

return_hmdb51 Ran
ran on a synthesized input
mit-han-lab/temporal-shift-module/ops/dataset_config.py
code served (permissive licence) · get_code("15b0c24622f53e08")
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 tuple, ndim 1, 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

torch.manual_seed(0)

ARGS = {
    'modality': 'RGB'
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
return_something Ran
ran on a synthesized input
mit-han-lab/temporal-shift-module/ops/dataset_config.py
code served (permissive licence) · get_code("dca73a0ccf302382")
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 tuple, ndim 1, 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

torch.manual_seed(0)

ARGS = {
    'modality': 'RGB'
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
return_ucf101 Ran
ran on a synthesized input
mit-han-lab/temporal-shift-module/ops/dataset_config.py
code served (permissive licence) · get_code("064ec89fbb984cf6")
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 tuple, ndim 1, 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 torch.nn as nn

torch.manual_seed(0)

# The function return_ucf101 takes a single parameter: modality
# It returns a tuple of strings based on the modality value
# Valid modalities are 'RGB' and 'Flow'

ARGS = {
    'modality': 'RGB'
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
bninception Not yet run
unverified (harvested, no recorded run)
mit-han-lab/temporal-shift-module/archs/bn_inception.py
code served (permissive licence) · get_code("c89c29bd79c97227")
How it ran

no invocation recorded.

make_temporal_shift Not yet run
unverified (harvested, no recorded run)
mit-han-lab/temporal-shift-module/ops/temporal_shift.py
code served (permissive licence) · get_code("ea903b20756dc01d")
How it ran

no invocation recorded.

torch_params Not yet run
unverified (harvested, no recorded run)
mit-han-lab/temporal-shift-module/tsm_fpga/mobilenet_v2_tfslim.py
code served (permissive licence) · get_code("47e316f6d90b3490")
How it ran

no invocation recorded.

torch_to_conv_state Not yet run
unverified (harvested, no recorded run)
mit-han-lab/temporal-shift-module/tsm_fpga/mobilenet_v2_tfslim.py
code served (permissive licence) · get_code("9823b80aaa256ebd")
How it ran

no invocation recorded.

torch_to_linear_state Not yet run
unverified (harvested, no recorded run)
mit-han-lab/temporal-shift-module/tsm_fpga/mobilenet_v2_tfslim.py
code served (permissive licence) · get_code("b85fde19d195b87f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 8 are also present in other papers whose code we hold (8 with at least one paper dated earlier, 1 the same month, 3 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.

FunctionAlso present inEarliest-datedOthers named
conv_1x1_bn 31 other papers
19 dated earlier, 1 the same month, 10 later, 1 same year, order not determinable · 2 only as an assembly brick
1703.07402 (2017-03)
Simple Online and Realtime Tracking with a Deep Association Metric
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
and 28 more not named here
conv_bn 18 other papers
14 dated earlier, 4 later · 1 only as an assembly brick
1611.06403 (2016-11)
Deep Outdoor Illumination Estimation
1703.07402 (2017-03)
Simple Online and Realtime Tracking with a Deep Association Metric
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
and 15 more not named here
make_divisible 12 other papers
11 dated earlier, 1 later · 1 only as an assembly brick
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1801.04381 (2018-01)
MobileNetV2: Inverted Residuals and Linear Bottlenecks
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
and 9 more not named here
bninception 2 other papers
2 dated earlier
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
2005.06803 (2020-05)
TAM: Temporal Adaptive Module for Video Recognition
make_temporal_shift 2 other papers
2 dated earlier
1608.00859 (2016-08)
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
torch_params 1 other paper
1 dated earlier
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
torch_to_conv_state 1 other paper
1 dated earlier
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding
torch_to_linear_state 1 other paper
1 dated earlier
1811.08383 (2018-11)
TSM: Temporal Shift Module for Efficient Video Understanding

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 tackle catastrophic forgetting problem in the context of class-incremental learning for video recognition, which has not been explored actively despite the popularity of continual learning. Our framework addresses this challenging task by introducing time-channel importance maps and exploiting the importance maps for learning the representations of incoming examples via knowledge distillation. We also incorporate a regularization scheme in our objective function, which encourages individual features obtained from different time steps in a video to be uncorrelated and eventually improves accuracy by alleviating catastrophic forgetting. We evaluate the proposed approach on brand-new splits of class-incremental action recognition benchmarks constructed upon the UCF101, HMDB51, and Something-Something V2 datasets, and demonstrate the effectiveness of our algorithm in comparison to the existing continual learning methods that are originally designed for image data.

For agents

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

get_harvested_code_for_paper("2203.13611")
get_code_for_paper("2203.13611")
have("2203.13611")

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

curl https://syntology.ai/api/ran/2203.13611.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.13611.svg)](https://syntology.ai/paper/2203.13611)

Connect an agent — have() is free.