SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.09702 · 2019

BMN: Boundary-Matching Network for Temporal Action Proposal Generation

arXiv · PDF · Open in the Atlas

Code that ran

11 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; 2 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 3 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/1907.09702.json · badge: /api/ran/1907.09702.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
JJBOY/BMN-Boundary-Matching-Network community (classifier label)
classifier basis not recorded on the link
11 ran · 0 no recorded run
FunctionStatusWhere it lives
bmn_loss_func Ran
ran on a synthesized input
JJBOY/BMN-Boundary-Matching-Network/loss_function.py
code served (permissive licence) · get_code("fe434fb9c3f06e84")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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)
np.random.seed(0)

# Create small tensors for batch processing
batch_size = 2
temporal_dim = 4
bm_dim = 3

# pred_bm: shape (batch_size, 2, bm_dim) - contains regression and classification scores
pred_bm = torch.rand(batch_size, 2, bm_dim)

# pred_start: shape (batch_size, temporal_dim) - temporal action localization start predictions
pred_start = torch.rand(batch_size, temporal_dim)

# pred_end: shape (batch_size, temporal_dim) - temporal action localization end predictions
pred_end = torch.rand(batch_size, temporal_dim)

# gt_iou_map: shape (batch_size, bm_dim) - ground truth IoU map
gt_iou_map = torch.rand(batch_size, bm_dim)

# gt_start: shape (batch_size, temporal_dim) - ground truth start labels (binary)
gt_start = torch.randint(0, 2, (batch_size, temporal_dim)).float()

# gt_end: shape (batch_size, temporal_dim) - ground truth end labels (binary)
gt_end = torch.randint(0, 2, (batch_size, temporal_dim)).float()

# bm_mask: shape (batch_size, bm_dim) - binary mask for boundary matching
bm_mask = torch.randint(0, 2, (batch_size, bm_dim)).float()

ARGS = {
    "pred_bm": pred_bm,
    "pred_start": pred_start,
    "pred_end": pred_end,
    "gt_iou_map": gt_iou_map,
    "gt_start": gt_start,
    "gt_end": gt_end,
    "bm_mask": bm_mask,
}
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
getDatasetDict Ran
ran on a synthesized input
JJBOY/BMN-Boundary-Matching-Network/post_processing.py
code served (permissive licence) · get_code("13551e06a372ae9c")
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 dict. 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 pandas as pd
import json
import tempfile
import os

# Create temporary files for CSV and JSON
temp_dir = tempfile.mkdtemp()
csv_file = os.path.join(temp_dir, 'video_info.csv')
json_file = os.path.join(temp_dir, 'video_anno.json')

# Create sample CSV data with a validation subset entry
csv_data = pd.DataFrame({
    'video': ['video_001', 'video_002'],
    'subset': ['validation', 'train']
})
csv_data.to_csv(csv_file, index=False)

# Create sample JSON annotation data
json_data = {
    'video_001': {
        'duration_frame': 150,
        'duration_second': 5.0,
        'feature_frame': 100,
        'annotations': [
            {'segment': [0, 2], 'label': 'action1'},
            {'segment': [2, 4], 'label': 'action2'}
        ]
    },
    'video_002': {
        'duration_frame': 200,
        'duration_second': 8.0,
        'feature_frame': 120,
        'annotations': [
            {'segment': [1, 3], 'label': 'action3'}
        ]
    }
}

with open(json_file, 'w') as f:
    json.dump(json_data, f)

# Define ARGS dict
ARGS = {
    'opt': {
        'video_info': csv_file,
        'video_anno': json_file
    }
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
get_mask Ran
ran on a synthesized input
JJBOY/BMN-Boundary-Matching-Network/loss_function.py
code served (permissive licence) · get_code("1cd5e9eec5a11010")
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 Tensor, ndim 2, dtype family float, shape (4, 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 numpy as np

torch.manual_seed(0)

# Analyze the function: get_mask takes a single parameter 'tscale' which is used as:
# - An integer to create a [tscale, tscale] numpy array
# - Loop bounds (range(tscale))
# So tscale should be a small integer

tscale = 4

ARGS = {
    "tscale": tscale
}
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 Tensor, ndim 2, dtype family float, shape (4, 4) — shape (4, 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
interpolated_prec_rec Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JJBOY/BMN-Boundary-Matching-Network/Evaluation/eval_proposal.py
pointer only (licence: MIT); the stored copy get_code serves, from Ontheway361/BSN_pytorch, is pointer only (licence: NONE) · get_code("81aab88321de62c2")
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 Ontheway361/BSN_pytorch, 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.

ioa_with_anchors Ran
ran on a synthesized input
JJBOY/BMN-Boundary-Matching-Network/utils.py
code served (permissive licence) · get_code("49b3db69edc148a7")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np

# The function ioa_with_anchors takes 4 parameters:
# - anchors_min: array of minimum anchor values
# - anchors_max: array of maximum anchor values
# - box_min: minimum value of the box
# - box_max: maximum value of the box
#
# The function performs element-wise operations on these arrays,
# so they should be numpy arrays with compatible shapes.

# Create small numpy arrays for testing
anchors_min = np.array([0.0, 1.0, 2.0, 3.0])
anchors_max = np.array([2.0, 3.0, 4.0, 5.0])
box_min = np.array([0.5, 1.5, 1.5, 3.5])
box_max = np.array([1.5, 2.5, 3.5, 4.5])

ARGS = {
    'anchors_min': anchors_min,
    'anchors_max': anchors_max,
    'box_min': box_min,
    'box_max': box_max
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
iou_with_anchors Ran
ran on a synthesized input
JJBOY/BMN-Boundary-Matching-Network/utils.py
code served (permissive licence) · get_code("1ac2acb4c84fccca")
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 ndarray, ndim 1, dtype family float, shape (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 numpy as np

# Construct valid arguments for iou_with_anchors
# The function computes Jaccard/IoU scores between anchors and a box
# All parameters are 1D arrays representing intervals (min and max values)

anchors_min = np.array([0.0, 1.0, 2.0, 3.0])
anchors_max = np.array([1.0, 2.0, 3.0, 4.0])
box_min = np.array(0.5)
box_max = np.array(2.5)

ARGS = {
    "anchors_min": anchors_min,
    "anchors_max": anchors_max,
    "box_min": box_min,
    "box_max": box_max,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (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
load_json Ran
ran; our contract draft was wrong, not the code
JJBOY/BMN-Boundary-Matching-Network/dataset.py
code served (permissive licence) · get_code("1e0bb35d27bdc115")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file with sample data
temp_dir = tempfile.mkdtemp()
json_file_path = os.path.join(temp_dir, "test.json")

sample_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "object"}
}

with open(json_file_path, 'w') as f:
    json.dump(sample_data, f)

ARGS = {
    "file": json_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
load_json Ran
ran; our contract draft was wrong, not the code
JJBOY/BMN-Boundary-Matching-Network/post_processing.py
code served (permissive licence) · get_code("e924a491a8d3290b")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file with sample data
temp_dir = tempfile.mkdtemp()
json_file_path = os.path.join(temp_dir, "test_data.json")

sample_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "object"}
}

with open(json_file_path, 'w') as f:
    json.dump(sample_data, f)

ARGS = {
    "file": json_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
segment_iou Ran
ran, honoured the contract we drafted
JJBOY/BMN-Boundary-Matching-Network/Evaluation/eval_proposal.py
pointer only (licence: MIT); the stored copy get_code serves, from Ontheway361/BSN_pytorch, is pointer only (licence: NONE) · get_code("d0744a2fe3151508")
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 Ontheway361/BSN_pytorch, 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.

tem_loss_func Ran
ran on a synthesized input
JJBOY/BMN-Boundary-Matching-Network/loss_function.py
code served (permissive licence) · get_code("8c307a8103898153")
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 Tensor, ndim 0, dtype family float, shape () 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

torch.manual_seed(0)

# Create small tensors for pred_start, pred_end, gt_start, gt_end
# The function uses these tensors with .view(-1), so they can have any shape
# Make them distinct sizes to probe dimensions later
batch_size = 2
seq_len = 4

# pred_start and pred_end should be probability scores (values between 0 and 1)
pred_start = torch.rand(batch_size, seq_len)
pred_end = torch.rand(batch_size, seq_len)

# gt_start and gt_end are ground truth labels (0 or 1, or continuous values)
# Create labels with some positive (>0.5) and some negative (<=0.5) samples
gt_start = torch.tensor([
    [0.1, 0.8, 0.2, 0.9],
    [0.7, 0.3, 0.6, 0.4]
], dtype=torch.float32)

gt_end = torch.tensor([
    [0.2, 0.9, 0.1, 0.8],
    [0.6, 0.4, 0.7, 0.3]
], dtype=torch.float32)

ARGS = {
    "pred_start": pred_start,
    "pred_end": pred_end,
    "gt_start": gt_start,
    "gt_end": gt_end,
}
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 Tensor, ndim 0, dtype family float, shape () — shape () 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
wrapper_segment_iou Ran
ran, honoured the contract we drafted
JJBOY/BMN-Boundary-Matching-Network/Evaluation/eval_proposal.py
code served (permissive licence) · get_code("265572629e36af77")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned ndarray, ndim 2, dtype family float, shape (4, 3) 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 numpy as np

# Create target_segments: m x 2 array (m=3 segments)
target_segments = np.array([
    [1.0, 5.0],
    [10.0, 15.0],
    [20.0, 25.0]
])

# Create candidate_segments: n x 2 array (n=4 segments)
candidate_segments = np.array([
    [2.0, 4.0],
    [3.0, 6.0],
    [12.0, 14.0],
    [22.0, 28.0]
])

ARGS = {
    'target_segments': target_segments,
    'candidate_segments': candidate_segments
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (4, 3) — shape (4, 3) 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 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, 9 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 9 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.

FunctionAlso present inEarliest-datedOthers named
interpolated_prec_rec 13 other papers
2 dated earlier, 11 later
1804.05113 (2018-04)
Multilevel Language and Vision Integration for Text-to-Clip Retrieval
1806.02964 (2018-06)
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
1911.11462 (2019-11)
G-TAD: Sub-Graph Localization for Temporal Action Detection
and 10 more not named here
segment_iou 13 other papers
2 dated earlier, 11 later
1804.05113 (2018-04)
Multilevel Language and Vision Integration for Text-to-Clip Retrieval
1806.02964 (2018-06)
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
1911.11462 (2019-11)
G-TAD: Sub-Graph Localization for Temporal Action Detection
and 10 more not named here
load_json 3 other papers
3 later
2009.07641 (2020-09)
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
2204.01680 (2022-04)
TALLFormer: Temporal Action Localization with a Long-memory Transformer
2408.06437 (2024-08)
HAT: History-Augmented Anchor Transformer for Online Temporal Action Localization
ioa_with_anchors 2 other papers
2 later
1911.11462 (2019-11)
G-TAD: Sub-Graph Localization for Temporal Action Detection
2009.07641 (2020-09)
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
iou_with_anchors 2 other papers
2 later
1911.11462 (2019-11)
G-TAD: Sub-Graph Localization for Temporal Action Detection
2009.07641 (2020-09)
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
load_json 2 other papers
2 later
1911.11462 (2019-11)
G-TAD: Sub-Graph Localization for Temporal Action Detection
2009.07641 (2020-09)
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
getDatasetDict 1 other paper
1 later
2009.07641 (2020-09)
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
get_mask 1 other paper
1 later
2009.07641 (2020-09)
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
wrapper_segment_iou 1 other paper
1 later
2110.07058 (2021-10)
Ego4D: Around the World in 3,000 Hours of Egocentric Video

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

Temporal action proposal generation is an challenging and promising task which aims to locate temporal regions in real-world videos where action or event may occur. Current bottom-up proposal generation methods can generate proposals with precise boundary, but cannot efficiently generate adequately reliable confidence scores for retrieving proposals. To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map. Based on BM mechanism, we propose an effective, efficient and end-to-end proposal generation method, named Boundary-Matching Network (BMN), which generates proposals with precise temporal boundaries as well as reliable confidence scores simultaneously. The two-branches of BMN are jointly trained in an unified framework. We conduct experiments on two challenging datasets: THUMOS-14 and ActivityNet-1.3, where BMN shows significant performance improvement with remarkable efficiency and generalizability. Further, combining with existing action classifier, BMN can achieve state-of-the-art temporal action detection performance.

For agents

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

get_harvested_code_for_paper("1907.09702")
get_code_for_paper("1907.09702")
have("1907.09702")

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

curl https://syntology.ai/api/ran/1907.09702.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.09702.svg)](https://syntology.ai/paper/1907.09702)

Connect an agent — have() is free.