SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.03748 · 2019

Peeking into the Future: Predicting Future Person Activities and Locations in Videos

arXiv · PDF · Open in the Atlas

Code that ran

13 of 27 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 11 have no contract verdict; 1 failure of our instrument; 14 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/1902.03748.json · badge: /api/ran/1902.03748.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
google/next-prediction canonical (classifier label)
classifier basis: census
3 ran · 2 no recorded run
JunweiLiang/social-distancing-prediction community (classifier label)
classifier basis: plan_row
10 ran · 12 no recorded run
FunctionStatusWhere it lives
assign_to_device Ran
ran on a synthesized input
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/models.py
pointer only (licence: Apache-2.0) · get_code("4ec2e1cec0b40292")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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_out_size_same Ran
ran, honoured the contract we drafted
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/nn.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from xtarx/Unsupervised-Anomaly-Detection-with-Generative-Adversarial-Networks, is pointer only (licence: NONE) · get_code("40125e1efb67fa92")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

create_unique_color_float Ran
ran on a synthesized input
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/application_util/visualization.py
pointer only (licence: Apache-2.0) · get_code("cd3221a1bf9695cd")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

create_unique_color_uchar Ran
ran on a synthesized input
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/application_util/visualization.py
pointer only (licence: Apache-2.0) · get_code("6bb4e0327315f2d1")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

filter_future_act Ran
ran on a synthesized input
google/next-prediction/code/preprocess.py
code served (permissive licence) · get_code("44ebed645a926f5f")
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 list, ndim 1, dtype family int; 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)

# Construct arguments for filter_future_act
# The function expects:
# acts: tuple of (current_actid_list, current_dist_list, future_actid_list, future_dist_list)
# future_frame: int representing how many frames until the future

# Create small lists for activity IDs and distances
current_actid_list = [1, 2, 3]  # Current activity IDs
current_dist_list = [10, 5, 15]  # Distance to finish for each current activity
future_actid_list = [4, 5, 0]  # Future activity IDs (0 means no activity)
future_dist_list = [3, 8, 0]  # Distance to start for each future activity

acts = (current_actid_list, current_dist_list, future_actid_list, future_dist_list)
future_frame = 7

ARGS = {
    "acts": acts,
    "future_frame": future_frame
}
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 list, ndim 1, dtype family int — a list 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
find_past_trajs Ran
ran on a synthesized input
JunweiLiang/social-distancing-prediction/code/inference/inf_utils.py
pointer only (licence: Apache-2.0) · get_code("a84f3ff76e98471c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

gather_dt Ran
ran on a synthesized input
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/utils.py
pointer only (licence: Apache-2.0) · get_code("f59f0e3dab36d192")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

generate_anchors Ran
ran on a synthesized input
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/generate_anchors.py
pointer only (licence: Apache-2.0) · get_code("97cd5f6189f39c1f")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_scene Ran
ran on a synthesized input
google/next-prediction/code/utils.py
code served (permissive licence) · get_code("7209afc811349832")
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 str. 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 numpy as np

def get_scene(videoname_):
    """Get the scene camera from the ActEV videoname."""
    s = videoname_.split('_S_')[-1]
    s = s.split('_')[0]
    return s[:4]

# The function takes a videoname string and extracts the scene from it
# It expects a string with format containing '_S_' followed by scene info
# Example: "video_S_0123_other_stuff" -> "0123"

ARGS = {
    "videoname_": "video_S_0123_camera_info"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
process_args Ran
ran on a synthesized input
google/next-prediction/code/utils.py
code served (permissive licence) · get_code("d4500d8300440bc9")
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 Args. 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 os
import tempfile
import tensorflow as tf

class Args:
    def __init__(self):
        self.activation_func = 'relu'
        self.obs_len = 8
        self.pred_len = 12
        self.outbasepath = tempfile.gettempdir()
        self.modelname = 'test_model'
        self.runId = 1
        self.person_feat_path = tempfile.gettempdir()
        self.is_actev = True
        self.scene_h = 1080
        self.scene_w = 1920
        self.load_best = False
        self.load_from = None
        self.is_train = True
        self.num_epochs = 10
        self.keep_prob = 0.5

ARGS = {
    'args': Args()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Args — a Args output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Args 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
reconstruct Ran
ran; our contract draft was wrong, not the code
JunweiLiang/social-distancing-prediction/code/pred_models.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Jacobieee/ST-MR, is pointer only (licence: NONE) · get_code("fcf20886f0b38d3e")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

resize_img Ran
ran on a synthesized input
JunweiLiang/social-distancing-prediction/code/inference/inf_utils.py
pointer only (licence: Apache-2.0) · get_code("ec7bbfb0d2db3e6e")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

view_roi Ran
ran on a synthesized input
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/application_util/image_viewer.py
pointer only (licence: Apache-2.0) · get_code("3bfba2bd3a128be5")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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.

get_gpu_info_block Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/utils.py
pointer only (licence: Apache-2.0) · get_code("a22b5deaf7163110")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
google/next-prediction/code/models.py
code served (permissive licence) · get_code("31da21e094c7d778")
How it ran

no invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/pred_models.py
pointer only (licence: Apache-2.0) · get_code("6454fa29970866f9")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

get_video_meta Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/inference/inf_utils.py
pointer only (licence: Apache-2.0) · get_code("3e989a9edbc046bd")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

is_in_bounds Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/application_util/image_viewer.py
pointer only (licence: Apache-2.0) · get_code("43de09e526867380")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

nms Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/nn.py
pointer only (licence: Apache-2.0) · get_code("88997f58c436a3c5")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

nms_wrapper Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/utils.py
pointer only (licence: Apache-2.0) · get_code("11418a38d54c1c24")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

non_max_suppression Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/application_util/preprocessing.py
pointer only (licence: Apache-2.0) · get_code("e8fe9fcc53566f61")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

process_args Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/pred_utils.py
pointer only (licence: Apache-2.0) · get_code("00b7b47ee41437f0")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

read_data Not yet run
unverified (harvested, no recorded run)
google/next-prediction/code/utils.py
code served (permissive licence) · get_code("cf9a4a78c12b9663")
How it ran

no invocation recorded.

read_data Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/pred_utils.py
pointer only (licence: Apache-2.0) · get_code("07bdfb978bf79ac1")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

soft_nms Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/nn.py
pointer only (licence: Apache-2.0) · get_code("6c30c6855f89573f")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

tf_flatten Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/inference/Object_Detection_Tracking/deformable_helper.py
pointer only (licence: Apache-2.0) · get_code("12e6fdbf5080bbb4")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

wd_cost Not yet run
unverified (harvested, no recorded run)
JunweiLiang/social-distancing-prediction/code/pred_models.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Jacobieee/ST-MR, is pointer only (licence: NONE) · get_code("41ae2a5827588c68")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, JunweiLiang/social-distancing-prediction, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. 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. No invocation recorded.

Also present in other papers' code

Of 27 samples lifted from this paper's linked repositories, 27 carry a function identity and 0 do not. Of the 26 distinct functions with an identity, 7 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 6 later) and 19 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_out_size_same 6 other papers
4 dated earlier, 2 later
1511.06434 (2015-11)
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
1703.05921 (2017-03)
Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
1804.04391 (2018-04)
MGGAN: Solving Mode Collapse using Manifold Guided Training
and 3 more not named here
non_max_suppression 3 other papers
1 dated earlier, 2 later
1703.07402 (2017-03)
Simple Online and Realtime Tracking with a Deep Association Metric
2002.08397 (2020-02)
JRMOT: A Real-Time 3D Multi-Object Tracker and a New Large-Scale Dataset
2004.10934 (2020-04)
YOLOv4: Optimal Speed and Accuracy of Object Detection
create_unique_color_float 1 other paper
1 later
2412.17807 (2024-12)
Cross-View Referring Multi-Object Tracking
create_unique_color_uchar 1 other paper
1 later
2412.17807 (2024-12)
Cross-View Referring Multi-Object Tracking
reconstruct 1 other paper
1 later
2206.05712 (2022-06)
Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction
tf_flatten 1 other paper
1 dated earlier
1703.06211 (2017-03)
Deformable Convolutional Networks
wd_cost 1 other paper
1 later
2206.05712 (2022-06)
Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction

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

Deciphering human behaviors to predict their future paths/trajectories and what they would do from videos is important in many applications. Motivated by this idea, this paper studies predicting a pedestrian's future path jointly with future activities. We propose an end-to-end, multi-task learning system utilizing rich visual features about human behavioral information and interaction with their surroundings. To facilitate the training, the network is learned with an auxiliary task of predicting future location in which the activity will happen. Experimental results demonstrate our state-of-the-art performance over two public benchmarks on future trajectory prediction. Moreover, our method is able to produce meaningful future activity prediction in addition to the path. The result provides the first empirical evidence that joint modeling of paths and activities benefits future path prediction.

For agents

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

get_harvested_code_for_paper("1902.03748")
get_code_for_paper("1902.03748")
have("1902.03748")

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

curl https://syntology.ai/api/ran/1902.03748.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.03748.svg)](https://syntology.ai/paper/1902.03748)

Connect an agent — have() is free.