SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.00440 · CVPR · 2023

Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation

Haonan Wang, Limin Wang, Yuhan Zhu, Gangshan Wu, Guozhen Zhang, Youxin Chen

arXiv · PDF · Open in the Atlas

Code that ran

10 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (5 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 4 failures of our instrument; 2 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/2303.00440.json · badge: /api/ran/2303.00440.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
MCG-NJU/EMA-VFI community
Papers with Code archive
10 ran · 2 no recorded run
FunctionStatusWhere it lives
ConvBlock Ran
ran on a synthesized input · constructed an object; no result was computed
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("a9f0972fc8d657ae")
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, ConvBlock: 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_dim": 3,
    "out_dim": 16,
    "depths": 2,
    "act_layer": nn.PReLU,
}
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 ConvBlock — 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 ConvBlock 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
CrossScalePatchEmbed Ran
ran on a synthesized input · constructed an object; no result was computed
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("4d87dd873dd0cb76")
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, CrossScalePatchEmbed: 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
from timm.models.layers import DropPath, to_2tuple, trunc_normal_

torch.manual_seed(0)

ARGS = {
    "in_dims": [16, 32, 64],
    "embed_dim": 768,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CrossScalePatchEmbed — 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 CrossScalePatchEmbed 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
DWConv Ran
ran on a synthesized input · constructed an object; no result was computed
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("b5607e4cc9098c21")
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, DWConv: 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)

# DWConv.__init__ takes 'dim' parameter
dim = 4

# Create the model instance
model = nn.Module()

# Now we need to construct arguments for the forward method
# forward(self, x, H, W)
# x has shape (B, N, C) where C should match dim
# The forward method reshapes to (B, C, H, W) for conv2d
# Then reshapes back to (B, C, -1) which means (B, C, H*W)
# So N = H * W

B = 2  # batch size
H = 3  # height
W = 4  # width
N = H * W  # sequence length must equal H*W
C = dim

# Create input tensor of shape (B, N, C)
x = torch.randn(B, N, C)

ARGS = {
    'dim': dim,
}
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 DWConv — 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 DWConv 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
InterFrameAttention Ran
ran on a synthesized input
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("5d39fa7b2acea443")
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 math
from timm.models.layers import DropPath, to_2tuple, trunc_normal_

class InterFrameAttention(nn.Module):

    def __init__(self, dim, motion_dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0.0, proj_drop=0.0):
        super().__init__()
        assert dim % num_heads == 0, f'dim {dim} should be divided by num_heads {num_heads}.'
        self.dim = dim
        self.motion_dim = motion_dim
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = qk_scale or head_dim ** (-0.5)
        self.q = nn.Linear(dim, dim, bias=qkv_bias)
        self.kv = nn.Linear(dim, dim * 2, bias=qkv_bias)
        self.cor_embed = nn.Linear(2, motion_dim, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)
        self.motion_proj = nn.Linear(motion_dim, motion_dim)
        self.proj_drop = nn.Dropout(proj_drop)
        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            trunc_normal_(m.weight, std=0.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)
        elif isinstance(m, nn.Conv2d):
            fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
            fan_out //= m.groups
            m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
            if m.bias is not None:
                m.bias.data.zero_()

    def forward(self, x1, x2, cor, H, W, mask=None):
        B, N, C = x1.shape
        B, N, C_c = cor.shape
        q = self.q(x1).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3)
        kv = self.kv(x2).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
        cor_embed_ = self.cor_embed(cor)
        cor_embed = cor_embed_.reshape(B, N, self.num_heads, self.motion_dim // self.num_heads).permute(0, 2, 1, 3)
        k, v = (kv[0], kv[1])
        attn = q @ k.transpose(-2, -1) * self.scale
        if mask is not None:
            nW = mask.shape[0]
            attn = attn.view(B // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
            attn = attn.view(-1, self.num_heads, N, N)
            attn = attn.softmax(dim=-1)
        else:
            attn = attn.softmax(dim=-1)
        attn = self.attn_drop(attn)
        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
        c_reverse = (attn @ cor_embed).transpose(1, 2).reshape(B, N, -1)
        motion = self.motion_proj(c_reverse - cor_embed_)
        x = self.proj(x)
        x = self.proj_drop(x)
        return (x, motion)


INIT_ARGS = {
    'dim': 8,
    'motion_dim': 8,
    'num_heads': 2,
    'qkv_bias': False,
    'qk_scale': None,
    'attn_drop': 0.0,
    'proj_drop': 0.0,
}

ARGS = {
    'x1': torch.randn(2, 5, 8),
    'x2': torch.randn(2, 5, 8),
    'cor': torch.randn(2, 5, 2),
    'H': 4,
    'W': 3,
    'mask': None,
}

if __name__ == '__main__':
    model = InterFrameAttention(**INIT_ARGS)
    output = model(**ARGS)
    print("Output shapes:", output[0].shape, output[1].shape)
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
timm, torch — 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)
Mlp Ran
ran on a synthesized input · constructed an object; no result was computed
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("49e7751169736ead")
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, Mlp: 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
from timm.models.layers import DropPath, to_2tuple, trunc_normal_

torch.manual_seed(0)

ARGS = {
    "in_features": 4,
    "hidden_features": 8,
    "out_features": 4,
    "act_layer": nn.GELU,
    "drop": 0.1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Mlp — 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 Mlp 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
OverlapPatchEmbed Ran
ran on a synthesized input · constructed an object; no result was computed
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("bc9aa8676665e403")
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, OverlapPatchEmbed: 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
from timm.models.layers import DropPath, to_2tuple, trunc_normal_

torch.manual_seed(0)

class OverlapPatchEmbed(nn.Module):

    def __init__(self, patch_size=7, stride=4, in_chans=3, embed_dim=768):
        super().__init__()
        patch_size = to_2tuple(patch_size)
        self.patch_size = patch_size
        self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=stride, padding=(patch_size[0] // 2, patch_size[1] // 2))
        self.norm = nn.LayerNorm(embed_dim)
        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            trunc_normal_(m.weight, std=0.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)
        elif isinstance(m, nn.Conv2d):
            fan_out = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
            fan_out //= m.groups
            m.weight.data.normal_(0, math.sqrt(2.0 / fan_out))
            if m.bias is not None:
                m.bias.data.zero_()

    def forward(self, x):
        x = self.proj(x)
        _, _, H, W = x.shape
        x = x.flatten(2).transpose(1, 2)
        x = self.norm(x)
        return (x, H, W)

ARGS = {
    'patch_size': 7,
    'stride': 4,
    'in_chans': 3,
    'embed_dim': 4
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
timm, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type OverlapPatchEmbed — 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 OverlapPatchEmbed 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
depad_if_needed Ran
ran; our contract draft was wrong, not the code
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("def44daa823d60b3")
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 4, dtype family float, shape (2, 7, 6, 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 math

torch.manual_seed(0)

# Create a padded tensor: batch=2, height=7, width=6, channels=4
# This will be padded to match window_size multiples
x = torch.randn(2, 9, 8, 4)

# Original unpadded size: (batch=2, height=7, width=6, channels=4)
size = (2, 7, 6, 4)

# Window size for padding calculation
window_size = (4, 4)

ARGS = {
    "x": x,
    "size": size,
    "window_size": window_size,
}
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 4, dtype family float, shape (2, 7, 6, 4) — shape (2, 7, 6, 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
pad_if_needed Ran
ran; our contract draft was wrong, not the code
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("aa39c3cb6f9a4cb6")
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. 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)

# Construct arguments for pad_if_needed function
# Parameters: x (tensor), size (tuple), window_size (tuple)

# x: a 4D tensor with shape (B, H, W, C)
x = torch.randn(2, 5, 7, 4)  # (batch=2, height=5, width=7, channels=4)

# size: a tuple (n, h, w, c) representing the dimensions
# This should match x.shape
size = (2, 5, 7, 4)

# window_size: a tuple (window_h, window_w) for window partitioning
window_size = (2, 3)

ARGS = {
    'x': x,
    'size': size,
    'window_size': window_size
}
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 — 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: none by the harness; any seed is in the setup block
window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("9641bf1050805151")
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 3, dtype family float, shape (8, 12, 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

torch.manual_seed(0)

# Construct arguments for window_partition
# The function expects:
# - x: a tensor of shape (B, H, W, C) where H and W are divisible by window_size
# - window_size: a tuple or list of 2 elements [window_height, window_width]

B = 2  # batch size
H = 8  # height (divisible by window_size[0])
W = 6  # width (divisible by window_size[1])
C = 4  # channels

window_size = [4, 3]  # [window_height, window_width]

# Create a tensor with shape (B, H, W, C)
x = torch.randn(B, H, W, C)

ARGS = {
    'x': x,
    'window_size': window_size
}
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 3, dtype family float, shape (8, 12, 4) — shape (8, 12, 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
window_reverse Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("4b2da073b4d351d3")
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 4, dtype family float, shape (2, 4, 6, 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

torch.manual_seed(0)

# Analyze the function to understand what parameters are needed:
# - windows: tensor of shape (nwB, N, C) where nwB = num_windows * B
# - window_size: tuple of (height, width) for each window
# - H: total height
# - W: total width

# The function reverses a windowing operation:
# It takes windowed patches and reconstructs them into a full image

# Let's set up reasonable dimensions:
# - window_size = (2, 3) - small window
# - H = 4, W = 6 - small image dimensions (divisible by window size)
# - B = 2 - batch size
# - num_windows = (H // window_size[0]) * (W // window_size[1]) = 2 * 2 = 4
# - nwB = B * num_windows = 2 * 4 = 8
# - N = window_size[0] * window_size[1] = 2 * 3 = 6 (flattened window)
# - C = 4 - channels

window_size = (2, 3)
H = 4
W = 6
B = 2
num_windows = (H // window_size[0]) * (W // window_size[1])  # 2 * 2 = 4
nwB = B * num_windows  # 2 * 4 = 8
N = window_size[0] * window_size[1]  # 2 * 3 = 6
C = 4

# Create windows tensor: (nwB, N, C)
windows = torch.randn(nwB, N, C)

ARGS = {
    "windows": windows,
    "window_size": window_size,
    "H": H,
    "W": W,
}
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 4, dtype family float, shape (2, 4, 6, 4) — shape (2, 4, 6, 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
MotionFormer Not yet run
unverified (harvested, no recorded run)
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("faa0a3a2edc81e48")
How it ran

no invocation recorded.

MotionFormerBlock Not yet run
unverified (harvested, no recorded run)
MCG-NJU/EMA-VFI/model/feature_extractor.py
code served (permissive licence) · get_code("e3645b81274cf177")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 9 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
pad_if_needed
brick of this paper's assembly: helper
1 other paper
1 later
2406.09754 (2024-06)
LAVIB: A Large-scale Video Interpolation Benchmark
window_partition
brick of this paper's assembly: helper
1 other paper
1 later
2406.09754 (2024-06)
LAVIB: A Large-scale Video Interpolation Benchmark
window_reverse
brick of this paper's assembly: helper
1 other paper
1 later
2406.09754 (2024-06)
LAVIB: A Large-scale Video Interpolation Benchmark

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

Effectively extracting inter-frame motion and appearance information is important for video frame interpolation (VFI). Previous works either extract both types of information in a mixed way or devise separate modules for each type of information, which lead to representation ambiguity and low efficiency. In this paper, we propose a new module to explicitly extract motion and appearance information via a unified operation. Specifically, we rethink the information process in inter-frame attention and reuse its attention map for both appearance feature enhancement and motion information extraction. Furthermore, for efficient VFI, our proposed module could be seamlessly integrated into a hybrid CNN and Transformer architecture. This hybrid pipeline can alleviate the computational complexity of inter-frame attention as well as preserve detailed lowlevel structure information. Experimental results demonstrate that, for both fixed-and arbitrary-timestep interpolation, our method achieves state-of-the-art performance on various datasets. Meanwhile, our approach enjoys a lighter computation overhead over models with close performance. The source code and models are available at https://github.com/MCG-NJU/EMA-VFI.

For agents

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

get_harvested_code_for_paper("2303.00440")
get_code_for_paper("2303.00440")
have("2303.00440")

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

curl https://syntology.ai/api/ran/2303.00440.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.00440.svg)](https://syntology.ai/paper/2303.00440)

Connect an agent — have() is free.