Organizations: Department of Industrial Engineering, Tsinghua University, Beijing, China · Lab, Huawei Technologies Ltd, Beijing, China · Datadog AI Research.
Time-series anomaly detection (TSAD) requires identifying both immediate Point Anomalies and long-range Context Anomalies. However, existing foundation models face a fundamental trade-off: 1D temporal models provide fine-grained pointwise localization but lack a global contextual perspective, while 2D vision-based models capture global patterns but suffer from information bottlenecks due to a lack of temporal alignment and coarse-grained pointwise detection. To resolve this dilemma, we propose VETime, the first TSAD framework that unifies temporal and visual modalities through fine-grained visual-temporal alignment and dynamic fusion. VETime introduces a Reversible Image Conversion and a Patch-Level Temporal Alignment module to establish a shared visual-temporal timeline, preserving discriminative details while maintaining temporal sensitivity. Furthermore, we design an Anomaly Window Contrastive Learning mechanism and a Task-Adaptive Multi-Modal Fusion to adaptively integrate the complementary perceptual strengths of both modalities. Extensive experiments demonstrate that VETime significantly outperforms state-of-the-art models in zero-shot scenarios, achieving superior localization precision with lower computational overhead than current vision-based approaches. Code available at: https://github.com/yyyangcoder/VETime .
Figures & tables
Figure 1: Comparison of the previous TSAD methods and the proposed VETime. While existing methods often rely on single-modality or coarse visual mapping, VETime introduces fine-grained temporal alignment and dynamic fusion to bridge the gap between visual and temporal perceptions.
Figure 2: Overview of the proposed framework. The time series is first processed by a time-series encoder to extract temporal features FTS while simultaneously undergoing Traceable Image Conversion to generate visual input. Then visual features FV0 extracted from a frozen pre-trained image encoder are subsequently transformed into FV through Patch-level Temporal Alignment to reinforce their temporal positional association. Then, FTS and FV are input into the Anomaly Window Contrastive Learning to derive an anomaly-enhanced representation FA . Finally, a Task-adaptive Multi-modal Fusion module integrates all features ( FA , FTS , FV ). Final outputs FAD and FRec are mapped to the original sequence length via token projection for the respective anomaly classification and reconstruction heads.
Figure 3: The framework of Traceable Image Conversion and Patch-level Temporal Alignment.
Figure 4: An illustration of Anomaly window contrastive learning
Metric
Model
Univariate Datasets
Total
Total
Avg
IOPS
MGAB
NAB
NEK
Power
SED
Stock
TODS
UCR
WSD
YAHOO
1st
2nd
Rank
Affiliation-F1
VETime
90.53
68.03
88.57
79.56
78.78
97.31
69.60
85.85
85.06
94.31
97.15
04
04
2.55
TimeRCD
83.28
70.69
82.48
79.73
85.51
96.87
71.84
86.37
84.63
90.33
96.65
02
03
3.27
DADA †
89.37 *
67.66 *
86.56
95.40
69.79
65.18
98.77
76.89
72.21
93.92
92.20 *
02
00
4.00
TS-Pulse
68.76
67.33
70.80
73.05
69.94
67.44
67.93
67.90
67.70
68.22
70.05
00
00
6.64
MOMENT †
87.54 *
66.76 *
90.45 *
92.26
75.97
59.13
45.26
59.76
75.77
95.39
79.99 *
02
00
4.73
Table 1: Performance of VETime against zero-shot baselines on 26 public datasets (11 univariate and 15 multivariate). Asterisked (*) results are excluded from ranking due to data leakage of models marked with ( † ). Red : best, Blue : second best.
Metric
Method
NAB
YAHOO
SMAP
MSL
Affiliation -F1
VETime
88.57
97.15
98.83
92.78
VIT4TS
61.12
60.66
91.55
65.80
VLM4TS
70.37
64.25
94.76
66.15
VisualTimeAnomaly
62.46
61.03
91.65
86.20
AnomLLM
58.53
36.43
42.52
46.08
F1_T
VETime
44.31
91.54
70.21
50.38
Table 2: Performance of VETime against vision-based baselines (SMAP and MSL are univariate settings following VLM4TS ( He et al., 2026 ) ).
Table 7
Figure 5: Effective Receptive Field (ERF) analysis comparing 1D temporal and 2D visual branches across different anomaly types. ERFs are computed via tracking the gradient flow from the final anomaly output back to the raw 1D or 2D inputs, with (b) and (d) averaged across the entire targeted region. 1D temporal branch (a, b) is strictly confined to local contexts, whereas 2D visual branch (c, d) exhibits period-aligned attention peaks that capture cross-period global awareness.
Figure 9
Figure 8: Qualitative anomaly detection results. The top row displays the time series with ground-truth anomalies (red shading), followed by anomaly scores from TimeRCD, VLM4TS, and VETime.
Appendix figures & tables19 assets
Supplementary material from the paper’s appendix.
Appendix
Name
Domain
#TS
Avg Length
AR (%)
UCR
Misc.
228
67818.7
0.6
NAB
Web
28
5099.7
10.6
YAHOO
Web
259
1560.2
0.6
IOPS
Operations
17
72792.3
1.3
MGAB
Sensor
9
97777.8
0.2
SED
Energy
3
23332.3
4.1
Appendix
Table 5: Univariate Datasets
Name
Domain
#TS
Avg Length
AR (%)
MSL
Space
16
3119.4
5.1
PSM
Sensor
1
217624.0
11.2
SMAP
Space
27
7855.9
2.9
SMD
Server
22
25466.4
3.8
SWaT
ICS
2
207457.5
12.7
GHL
Reservoir
25
199001.0
1.1
Appendix
Table 6: Multivariate Datasets
Metric
Model
Univariate Datasets
Total
Total
Avg
IOPS
MGAB
NAB
NEK
Power
SED
Stock
TODS
UCR
WSD
YAHOO
1st
2nd
Rank
Full-Shot Models
Affiliation-F1
VETime
90.53
68.03
88.57
79.56
78.78
97.31
69.60
85.85
85.06
94.31
97.15
07
00
1.91
TranAD
83.19
67.28
90.28
85.02
71.56
61.03
57.94
52.76
73.31
84.34
76.08
00
04
3.45
USAD
71.08
67.81
91.54
71.13
76.48
55.60
35.92
47.90
76.00
65.10
53.05
00
02
4.36
OmniAnomaly
80.32
67.35
92.35
86.30
78.16
61.26
75.24
50.73
73.53
78.02
71.31
03
01
3.00
Appendix
Table 7: Performance of VETime (zero-shot) against full-shot baselines on 11 public univariate datasets. Red : best, Blue : second best.
Metric
Model
Multivariate Datasets
Additional Datasets
Total
Total
MSL
PSM
SMAP
SMD
SWaT
GHL
Daph.
Exath.
Gen.
GECCO
MIT
SVDB
LTDB
CATS
TAO
1st
2nd
Full-Shot Models
Affiliation-F1
VETime
87.02
77.27
87.06
88.94
75.45
74.93
84.61
99.90
75.41
87.63
75.16
73.03
78.28
72.08
75.41
12
01
TranAD
79.91
73.83
87.39
92.20
75.37
39.00
72.00
94.00
69.00
26.00
71.00
71.00
64.00
75.00
41.00
02
09
USAD
81.86
57.86
87.25
85.09
75.06
35.95
19.82
84.96
46.84
14.51
63.28
58.33
35.81
57.04
2.05
00
00
OmniAnomaly
83.15
58.17
91.38
85.82
73.39
40.90
67.74
93.89
68.63
18.28
70.95
71.96
64.86
74.32
20.31
01
05
Appendix
Table 8: Performance of VETime (zero-shot) against full-shot baselines on multivariate datasets. Red : best, Blue : second best.
Metric
Method
IOPS
MGAB
NAB
NEK
Power
SED
Stock
TODS
UCR
WSD
YAHOO
Affiliation-F1
TimeRCD
83.58 ± 0.62
70.19 ± 1.39
82.17 ± 1.99
78.56 ± 2.20
85.25 ± 1.71
96.90 ± 0.42
71.66 ± 1.05
86.66 ± 2.60
84.78 ± 0.40
90.12 ± 0.23
96.54 ± 0.37
DADA
73.00 ± 0.92
66.28 ± 1.66
84.51 ± 0.63
78.20 ± 1.81
68.05 ± 0.87
68.20 ± 1.58
96.55 ± 0.49
66.31 ± 0.32
66.36 ± 0.23
86.10 ± 0.73
90.46 ± 0.64
VETime
90.22 ± 0.66
68.18 ± 0.18
88.19 ± 0.43
79.95 ± 0.97
78.99 ± 0.33
97.95 ± 0.98
69.45 ± 0.61
85.43 ± 0.54
85.06 ± 0.24
94.28 ± 0.06
97.12 ± 0.16
VUS-PR
TimeRCD
21.82 ± 3.79
1.03 ± 0.06
24.42 ± 1.35
27.47 ± 2.65
21.17 ± 0.15
80.38 ± 0.90
76.72 ± 1.45
93.29 ± 1.69
23.08 ± 0.07
21.94 ± 2.71
84.23 ± 0.75
DADA
24.77 ± 1.85
0.62 ± 0.04
24.46 ± 0.79
64.82 ± 2.41
12.42 ± 0.64
6.43 ± 0.26
99.79 ± 0.02
57.47 ± 0.11
2.12 ± 0.65
30.38 ± 1.05
73.05 ± 0.47
VETime
30.84 ± 1.62
0.69 ± 0.02
32.84 ± 0.21
56.42 ± 2.71
11.85 ± 0.18
88.37 ± 2.24
76.21 ± 0.78
93.82 ± 0.53
24.67 ± 0.78
33.16 ± 0.65
87.92 ± 1.06
Appendix
Table 9: Performance comparison of supervised baselines re-trained on the same synthetic dataset (mean ± standard deviation over 5 runs). Best result is in red , second-best is in blue .
Metric
Method
IOPS
MGAB
NAB
NEK
Power
SED
Stock
TODS
UCR
WSD
YAHOO
Zero-Shot Models
Affiliation-F1
VETime
90.39 ± 3.10
68.17 ± 0.61
88.36 ± 3.38
74.96 ± 17.28
78.78 ± 0.00
97.08 ± 1.34
69.63 ± 0.54
85.84 ± 5.26
85.08 ± 1.54
93.25 ± 1.48
97.07 ± 1.79
TimeRCD
83.37 ± 3.67
70.71 ± 1.85
83.07 ± 9.54
82.39 ± 12.56
85.51 ± 0.00
96.48 ± 1.79
71.77 ± 1.49
86.58 ± 8.30
84.68 ± 1.86
90.36 ± 2.70
96.75 ± 1.29
DADA
89.61 ± 1.51
67.70 ± 0.40
87.51 ± 6.79
95.79 ± 0.13
69.79 ± 0.00
65.18 ± 2.03
98.83 ± 0.17
76.91 ± 12.69
72.20 ± 0.83
93.81 ± 2.72
92.33 ± 3.51
MOMENT
87.60 ± 2.02
67.08 ± 3.42
91.18 ± 4.32
91.53 ± 5.67
75.97 ± 0.00
58.19 ± 4.52
45.28 ± 0.91
59.76 ± 13.08
75.61 ± 2.55
95.46 ± 1.86
79.81 ± 3.79
TimesFM
81.93 ± 3.85
66.84 ± 0.95
79.63 ± 3.86
95.17 ± 1.76
69.88 ± 0.00
66.18 ± 3.40
97.51 ± 0.42
88.91 ± 4.93
69.97 ± 1.22
78.97 ± 1.75
91.34 ± 1.81
Appendix
Table 10: Performance of VETime against zero-shot and full-shot time-series baselines across 11 datasets (Mean ± 95% CI). Best result is in red , second-best is in blue .
Metric
Method
NAB
YAHOO
SMAP
MSL
Affiliation-F1
VETime
88.36 ± 3.38
97.07 ± 1.79
95.13 ± 3.72
90.66 ± 2.65
VIT4TS
64.64 ± 11.91
65.48 ± 3.67
93.55 ± 4.20
69.90 ± 22.83
VLM4TS
60.50 ± 13.28
64.27 ± 3.66
94.48 ± 3.42
64.63 ± 25.15
VisualTimeAnomaly
62.12 ± 4.25
60.80 ± 3.10
90.89 ± 3.76
86.23 ± 3.33
AnomLLM
58.23 ± 10.61
36.36 ± 4.24
42.03 ± 20.36
46.34 ± 20.64
F1T
VETime
44.22 ± 6.53
91.54 ± 1.65
66.04 ± 4.28
49.07 ± 6.93
Appendix
Table 11: Performance of VETime against vision-based baselines across 4 datasets (Mean ± 95% CI). Best result is in red , second-best is in blue .
Figure 9: Performance of VETime (strictly zero-shot) against zero-shot and full-shot models. Metrics: Average Rank (lower is better) across 4 metrics on different datasets.
Figure 10: Quantitative validation in feature separability between normal and anomalous representations. The clustering metrics clearly illustrate that the 2D visual transformation introduces global awareness, while the final fusion FAD maximizes the overall normal/anomalous separability.
Model
Params. (M)
Mem. (MB)
Avg. Time (ms)
NAB
WSD
YAHOO
Base
37.06
223.73
24.49
82.48 / 24.32
90.33 / 21.77
96.65 / 84.41
Dual-TS
160.49
928.52
48.19
80.84 / 30.28
88.87 / 27.24
96.81 / 87.25
VETime
157.96
787.41
51.02
88.57 / 32.98
94.31 / 33.85
97.15 / 88.61
Appendix
Table 12: Efficiency and performance comparison. Metrics are reported as Affiliation-F1 / VUS-PR (%). Best result is in red, second-best is in blue.
Model
Params. (M)
NAB
WSD
YAHOO
Resnet
25.63
78.41 / 22.96
75.17 / 13.57
70.85 / 15.75
ConvNeXt-Base
88.58
78.51 / 23.36
82.15 / 25.38
79.73 / 38.90
CLIP-Base
85.64
88.42 / 32.72
93.01 / 30.90
95.87 / 86.12
MAE-Base
85.64
88.57 / 32.98
94.31 / 33.85
97.15 / 88.61
MAE-Large
303.10
88.67 / 31.54
93.94 / 34.10
97.03 / 87.20
Appendix
Table 13: Ablation study and comparison of vision encoders (Affiliation-F1 / VUS-PR (%)). Best result is in red, second-best is in blue.
Figure 11: Qualitative comparison of different imaging strategies.
Imaging Strategies
Point
Contextual
Mixed
Base
85.65 / 67.31
77.18 / 23.89
83.90 / 39.35
(1) GAF
86.12 / 72.88
77.01 / 23.57
84.63 / 42.05
(2) RP
85.79 / 73.91
77.07 / 23.87
84.88 / 42.65
(3) Line plot
86.14 / 74.82
78.20 / 24.92
84.77 / 45.31
(4) Gray mappings
87.97 / 77.74
79.50 / 26.65
86.07 / 46.48
(5) Shuffled RGB mappings
88.75 / 78.42
78.94 / 25.51
84.43 / 46.36
Appendix
Table 14: Performance comparison under different imaging strategies (Affiliation-F1 / VUS-PR (%)). The time series from 11 univariate datasets are categorized as: Point (short-duration spikes), Contextual (long-duration structural shifts), and Mixed . Base : TS Encoder + Classifier. Shuffled RGB mappings : Temporal order shuffled before mapping and restored before alignment. Best result is in bold red , second-best is in bold blue .
Strategy
IOPS
MGAB
NAB
NEK
Power
SED
Stock
TODS
UCR
WSD
YAHOO
Direct feature-level fusion
87.40 / 22.67
67.51 / 0.73
83.31 /26.99
79.07/50.03
83.62/21.34
95.58/ 79.05
68.18/ 74.38
86.30 / 93.14
84.06/ 22.48
89.53 / 22.76
94.97 /80.33
Score-level fusion
86.78/20.35
67.09/0.71
81.91/ 27.04
81.09 / 60.98
83.96 / 21.36
93.87/77.53
68.33 /74.33
86.04/92.04
84.33 /22.32
89.51/22.43
94.22/ 82.34
Decision-level fusion
86.24/16.07
67.93 /0.70
80.89/25.50
79.50/48.66
83.04/21.16
95.79 /77.32
66.93/71.92
86.12/92.57
82.27/18.38
89.44/18.20
93.47/79.43
Alignment feature-level fusion
88.40 / 25.75
67.36/ 0.75
82.93 / 27.75
79.54 / 50.63
85.63 / 21.41
96.36 / 84.84
68.65 / 75.84
86.53 / 93.55
84.88 / 23.37
90.56 / 24.70
95.19 / 83.82
Appendix
Table 15: Performance comparison of different multimodal fusion strategies (Affiliation-F1 / VUS-PR (%)). Best result is in red , second-best is in blue .
Variant
LMSE
Law
Le
NAB
WSD
YAHOO
Base
82.93 / 27.75
90.56 / 24.70
95.19 / 83.82
Only LMSE
✓
82.05 / 27.64
90.10 / 24.86
95.20 / 83.29
Only Law
✓
83.99 / 29.52
90.11 / 26.30
96.86 / 85.31
w/o Le
✓
✓
84.62 / 28.81
90.72 / 27.47
96.64 / 85.56
w/o LMSE
✓
✓
86.96 / 28.44
90.87 / 28.63
96.88 / 86.58
w/o Law
✓
✓
86.84 / 31.23
91.63 / 29.00
97.11 / 87.26
Appendix
Table 16: Ablation study on training objectives (Affiliation-F1 / VUS-PR (%)). Base: LBCE . Best result is in red, second-best is in blue.
Variant
TIC
PTA
AWCL
TMF
IOPS
MGAB
NAB
NEK
Power
SED
Stock
TODS
UCR
WSD
YAHOO
Base
83.28/20.23
70.69 / 1.05
82.48/24.32
79.73 /27.88
85.51/21.25
96.87/80.75
71.84 / 77.28
86.37/93.46
84.63/23.09
90.33/21.77
96.65/84.41
V1
✓
87.40/22.67
67.51/0.73
83.31/26.99
79.07/50.03
83.62/21.34
95.58/79.05
68.18/74.38
86.30/93.14
84.06/22.48
89.53/22.76
94.97/80.33
V2
✓
✓
88.40/25.75
67.36/0.75
82.93/27.75
79.54/50.63
85.63 / 21.41
96.36/84.84
68.65/75.84
86.53 /93.55
84.88 /23.37
90.56/24.70
95.19/83.82
V3
✓
✓
✓
90.53/26.15
68.23/0.77
83.99/29.52
79.74 /53.10
85.78 / 21.48
97.16 /86.94
70.89 / 76.58
86.73 /93.76
85.06 /23.99
90.11/26.30
96.86/85.31
V4
✓
✓
✓
90.84 / 28.15
68.73 / 0.78
86.84 / 31.23
79.32/ 55.38
79.08/11.54
96.79/ 87.39
69.07/75.68
85.60/ 93.90
84.46/ 24.83
91.63 / 29.00
97.11 / 87.26
V5
✓
✓
90.56/26.26
67.22/0.75
83.23/24.81
78.85/48.04
78.63/11.33
95.78/85.37
69.60/75.60
86.05/93.20
84.75/24.40
90.54/24.91
96.06/82.62
Appendix
Table 17: Ablation on all 11 datasets (Affiliation-F1 / VUS-PR (%)). Best results are in red, and second-best are in blue. Base: TS Encoder + Classifier, TIC: Traceable Image Conversion, PTA: Patch-level Temporal Alignment, AWCL: Anomaly Window Contrastive Learning, TMF: Task-adaptive Multi-modal Fusion.
Model
Component
NAB
WSD
YAHOO
PTA
w/o adaptive folding
87.81 / 29.99
91.49 / 30.41
97.10 / 86.70
w/o positional encoding
88.16 / 30.27
92.29 / 31.18
97.25 / 86.81
w/o attention
85.69 / 29.88
91.57 / 29.46
96.92 / 85.53
AWCL
w/o inter-window contrast
86.69 / 31.17
92.85 / 30.54
97.15 / 87.29
w/o intra-window contrast
86.15 / 30.86
92.93 / 30.57
97.77 / 88.29
TMF
Concatenation
85.07 / 28.54
89.80 / 26.39
95.69 / 85.72
Appendix
Table 18: Ablation study grouped by model components: PTA (Patch-level Temporal Alignment), AWCL (Anomaly Window Contrastive Learning), and TMF (Task-adaptive Multi-modal Fusion). Metrics are reported as Affiliation-F1 / VUS-PR (%). Best result is in red, second-best is in blue.
Figure 12: Initial time series and mapping images.
Figure 13: Qualitative visualization of anomaly detection results. Blue curve: original time series; red markers: ground-truth anomaly labels; green curve: predicted anomaly scores.
Time-Series Anomaly Detection identifies unusual patterns or events in sequential data, from sensor readings and network traffic to health and industrial telemetry.
Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems. Existing methods require training one specific model for each dataset, which exhibits limited generalization capability across different target datasets, hindering anomaly detection performance in various scenarios with scarce training data. To address this limitation, foundation models have emerged as a promising direction. However, existing approaches either repurpose large language models (LLMs) or construct largescale time series datasets to develop general anomaly detection foundation models, and still face challenges caused by severe cross-modal gaps or in-domain heterogeneity. In this paper, we investigate the applicability of large-scale vision models to TSAD. Specifically, we adapt a visual Masked Autoencoder (MAE) pretrained on ImageNet to the TSAD task. However, directly transferring MAE to TSAD introduces two key challenges: overgeneralization and limited local perception. To address these challenges, we propose VAN-AD, a novel MAE-based framework for TSAD. To alleviate the over-generalization issue, we design an Adaptive Distribution Mapping Module (ADMM), which maps the reconstruction results before and after MAE into a unified statistical space to amplify discrepancies caused by abnormal patterns. To overcome the limitation of local perception, we further develop a Normalizing Flow Module (NFM), which combines MAE with normalizing flow to estimate the probability density of the current window under the global distribution. Extensive experiments on nine real-world datasets demonstrate that VAN-AD consistently outperforms existing state-of-the-art methods across multiple evaluation metrics.We make our code and datasets available at https://github.com/PenyChen/VAN-AD.
PengYu Chen, Shang Wan, Xiaohou Shi +3
School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications, Beijing 100876, China · China Telecom Research Institute Beijing, China · Department of Computer Science, Missouri University of Science and Technology, Rolla, MO 65409 USA
Time series anomaly detection is a crucial task in various domains, including finance, healthcare, and industry. However, existing methods often struggle to generalize across different datasets, especially when anomalies are subtle or context-dependent. To solve this issue, we introduce ChronosAD, a novel architecture for anomaly detection that uses a time series foundation model as a feature extractor. Specifically, it employs a two-stage pipeline: first, it uses the foundation model to extract embeddings for each time series in a zero-shot manner. Then, a custom-developed Temporal Block, composed of Bidirectional Long Short-Term Memory (BiLSTM) and Multi-Head Attention, refines these embeddings to capture temporal dependencies and highlight salient patterns. Unlike previous approaches, our model requires minimal task-specific tuning and demonstrates robust generalization across a wide range of domains, including industrial, medical, cyber-physical, and automotive systems. Extensive experiments on 11 benchmarks show that ChronosAD outperforms existing methods by 4.72% in AUC and 6.60% in AP on average. The source code is available at https://github.com/intelligolabs/ChronosAD.
Uzair Khan, Luigi Capogrosso, Francesco Biondani +4
University of Verona · Interdisciplinary Transformation University of Austria · ETH Zurich
Zero-shot anomaly detection (ZSAD) requires detecting and localizing anomalies without access to target-class anomaly samples. Mainstream methods rely on vision-language models (VLMs) such as CLIP: they build hand-crafted or learned prompt sets for normal and abnormal semantics, then compute image-text similarities for open-set discrimination. While effective, this paradigm depends on a text encoder and cross-modal alignment, which can lead to training instability and parameter redundancy. This work revisits the necessity of the text branch in ZSAD and presents VisualAD, a purely visual framework built on Vision Transformers. We introduce two learnable tokens within a frozen backbone to directly encode normality and abnormality. Through multi-layer self-attention, these tokens interact with patch tokens, gradually acquiring high-level notions of normality and anomaly while guiding patches to highlight anomaly-related cues. Additionally, we incorporate a Spatial-Aware Cross-Attention (SCA) module and a lightweight Self-Alignment Function (SAF): SCA injects fine-grained spatial information into the tokens, and SAF recalibrates patch features before anomaly scoring. VisualAD achieves state-of-the-art performance on 13 zero-shot anomaly detection benchmarks spanning industrial and medical domains, and adapts seamlessly to pretrained vision backbones such as the CLIP image encoder and DINOv2. Code: https://github.com/7HHHHH/VisualAD
Yanning Hou, Peiyuan Li, Zirui Liu +4
College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China · School of Artificial Intelligence, Anhui University, Hefei, China · State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Anhui University, Hefei, China