ARXIV:2602.10549 · VIDEO SURVEILLANCE AI · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance

arXiv

Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization. Text provides explicit semantic information that can enhance anomaly characterization and reduce false alarms.

METHOD

Full abstract

Weakly supervised multimodal video anomaly detection has gained significant attention, yet the potential of the text modality remains under-explored. Text provides explicit semantic information that can enhance anomaly characterization and reduce false alarms. However, extracting effective text features is challenging due to the inability of general-purpose language models to capture anomaly-specific nuances and the scarcity of relevant descriptions. Furthermore, multimodal fusion often suffers from redundancy and imbalance. To address these issues, we propose a novel text-guided framework. First, we introduce an in-context learning-based multi-stage text augmentation mechanism to generate high-quality anomaly text samples for fine-tuning the text feature extractor. Second, we design a multi-scale bottleneck Transformer fusion module that uses compressed bottleneck tokens to progressively integrate information across modalities, mitigating redundancy and imbalance. Experiments on UCF-Crime and XD-Violence demonstrate state-of-the-art performance.

RESULT

ScienceToStartup currently rates this 5.0/10 on the public viability pass. Experiments on UCF-Crime and XD-Violence demonstrate state-of-the-art performance.

WHY NOW

Video Surveillance AI moved forward this cycle; last verified April 2026. Public score 5.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score5.0

PainLeverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

ARXIV:2602.10549 · VIDEO SURVEILLANCE AI · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance

arXiv

Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

METHOD

Full abstract

RESULT

ScienceToStartup currently rates this 5.0/10 on the public viability pass. Experiments on UCF-Crime and XD-Violence demonstrate state-of-the-art performance.

WHY NOW

Video Surveillance AI moved forward this cycle; last verified April 2026. Public score 5.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score5.0

PainLeverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Paper Pack

10.48550/arXiv.2602.10549

Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance

Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.

Abstract

Source availability

PDF linked

The paper record includes a public PDF URL.

Extraction status

Derived fallback

Read summaries are estimated from adjacent metadata, not verified extraction rows.

Proof status

unverified

0 refs; 0 sources; 17% coverage.

What was readable

linkedon filenot materializedderived fallback67 indexednot indexed

Derived fallback: Estimated from adjacent evidence; not verified from source.

Viability

5.0

Time to MVP

MVP estimate missing

Commercial

No commercial flags on file

Export

Preparing verified analysis

lens / founder

PROBLEM

METHOD

RESULT

ScienceToStartup currently rates this 5.0/10 on the public viability pass. Experiments on UCF-Crime and XD-Violence demonstrate state-of-the-art performance.

WHY NOW

Video Surveillance AI moved forward this cycle; last verified April 2026. Public score 5.0/10.

Claim map

Abstract-backed public claims while anchored extraction refreshes.

Strong 0Mixed 0Weak 4

Evidencepartial
Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization. Text provides explicit semantic information that can enhance anomaly characterization and reduce false alarms.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Weakly supervised multimodal video anomaly detection has gained significant attention, yet the potential of the text modality remains under-explored. Text provides explicit semantic information that can enhance anomaly characterization and reduce false alarms.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
ScienceToStartup currently rates this 5.0/10 on the public viability pass. Experiments on UCF-Crime and XD-Violence demonstrate state-of-the-art performance.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial
Evidencepartial
Video Surveillance AI moved forward this cycle; last verified April 2026. Public score 5.0/10.
Implicationpartial
Abstract-backed fallback claim; anchored extraction has not materialized a public claim row yet.
Verificationpartial
partial

Constellation map

Paper-native neighborhood for concepts, methods, materials, markets, and competitors. Missing lanes stay labeled instead of disappearing behind commercialization gates.

Open full Signal Canvas

Concepts

not indexed

Methods

Materials

PDF linked

Markets

Video Surveillance AI

Competitors

not indexed

Competitive landscape

Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.

Segment

Video Surveillance AI

Adoption evidence

No public code link in the paper record yet

Commercial read

5.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Buzz

No indexed public discussion is attached to 2602.10549 yet. That is a visibility signal, not a blank module: the monitor is watching the public channels below.

Hacker News

Not indexed yet

Bluesky

Not indexed yet

PDF

Preview the source document here, or use the hero PDF action for a new tab.

References(67)

Surveillance Video-and-Language Understanding: From Small to Large Multimodal Models

2025Tongtong Yuan, Xuange Zhang et al.

TDSD: Text-Driven Scene-Decoupled Weakly Supervised Video Anomaly Detection

2024Shengyang Sun, Jiashen Hua et al.

Leveraging Multi-Modality and Enhanced Temporal Networks for Robust Violence Detection

2024Gwangho Na, Jaepil Ko et al.

Event-driven weakly supervised video anomaly detection

2024Shengyang Sun, Xiaojin Gong

MECOM: A Meta-Completion Network for Fine-Grained Recognition With Incomplete Multi-Modalities

2024Xiu-Shen Wei, Hong-Tao Yu et al.

Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection

2024Shengyang Sun, Xiaojin Gong

Abnormal Ratios Guided Multi-Phase Self-Training for Weakly-Supervised Video Anomaly Detection

2024Haoyue Shi, Le Wang et al.

Caption-Guided Interpretable Video Anomaly Detection Based on Memory Similarity

2024Yuzhi Shi, Takayoshi Yamashita et al.

Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges

2023Tongtong Yuan, Xuange Zhang et al.

VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detection

2023Peng Wu, Xu Zhou et al.

Weakly supervised point cloud segmentation via deep morphological semantic information embedding

2023Wenhao Xue, Yang Yang et al.

Scoreformer: Score Fusion-Based Transformers for Weakly-Supervised Violence Detection

2023Yang Xiao, Liejun Wang et al.

TEVAD: Improved video anomaly detection with captions

2023Weiling Chen, K. Ma et al.

Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach

2023Junjie Zhang, Ruobing Xie et al.

Few-shot In-context Learning on Knowledge Base Question Answering

2023Tianle Li, Xueguang Ma et al.

Instruction Tuning with GPT-4

2023Baolin Peng, Chunyuan Li et al.

Long-Short Temporal Co-Teaching for Weakly Supervised Video Anomaly Detection

2023Shengyang Sun, Xiaojin Gong

Decoupled Multimodal Distilling for Emotion Recognition

2023Yong Li, Yuan-Zheng Wang et al.

Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection

2023Shengyang Sun, Xiaojin Gong

Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning

2023Antoine Yang, Arsha Nagrani et al.

Showing 20 of 67 references

CITED BY

No citing papers are indexed in the public S2S graph yet. This is an explicit zero-signal state, not a hidden lookup.

Foundation

Prior WorkWeakly-Supervised Spatiotemporal Anomaly Detection

5.0

Prior WorkLayer-Specific Lipschitz Modulation for Fault-Tolerant Multimodal Representation Learning

5.0

Extension

Builds On ThisOut of Context: Reliability in Multimodal Anomaly Detection Requires Contextual Inference

4.0

Builds On ThisVisual Prompting Meets Feature Reconstruction-Based Anomaly Detection with Dual-Teacher Supervision

0.0

Builds On ThisUnveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization

2.0

Commercially relevant

Higher ViabilityTowards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction

7.0

Higher ViabilityExploring Multimodal Prompts For Unsupervised Continuous Anomaly Detection

7.0

Higher ViabilityAre Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild

6.0

Higher ViabilityWMoE-CLIP: Wavelet-Enhanced Mixture-of-Experts Prompt Learning for Zero-Shot Anomaly Detection

7.0

Higher ViabilityQVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection

7.0

Conflicting

none indexed

Owned Distribution

Subscribe to the weekly brief

Get the weekly shortlist of commercializable papers, benchmark movers, and proof receipts that matter for product execution.

Agent drawer

5 surfaces preserved for agents. Humans can ignore.

Developer contracts, payload previews, evidence maps, and run controls stay here instead of the Read, Build, and Track workspace.

Run context

Paper: 2602.10549
Route: /paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance
Active tab: read
Artifact: enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance

Available agents

Read extractor
Build planner
Track monitor
Competitive mapper
Related-paper scout

API/MCP endpoints

REST paper pack API/api/v1/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance/paper-pack
REST build passport API/api/v1/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance/build-passport
REST OpenAPI/api/openapi.json
MCP descriptor/api/mcp
MCP resourcesciencetostartup://surfaces/paper-workspace

Tool contracts

paper_packbuild_passportopportunity_kernelforesightsource_proofevidence_state

Payload preview

Inspect payload

{
  "contract_version": "paper-r2",
  "paper_id": "4c1e29fe-a3e1-40ca-9fd9-8586e797121a",
  "arxiv_id": "2602.10549",
  "canonical_route": "/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance",
  "active_tab": "synced from current hash by the drawer client",
  "selected_artifact": "enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance",
  "endpoints": {
    "paper_pack": "/api/v1/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance/paper-pack",
    "build_passport": "/api/v1/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance/build-passport",
    "mcp_resource": "sciencetostartup://surfaces/paper-workspace"
  }
}

Schema validation

paper-r2 contract: present
JSON-LD twin: SSR emitted
OpenAPI path parity: /api/openapi.json
MCP resource parity: paper-workspace

Job trace

queued: drawer opened by user action
running: inspect or copy payload
succeeded: payload available in SSR
failed: route errors appear in evidence cards

Evidence map

sources used: page freshness, source proof anchors, JSON-LD
missing sources: exposed by PaperPack and EvidenceState chips
derived fallbacks: marked unverified before handoff

Page Freshness

Canonical route, proof status, last verified, refs, sources, and coverage.

Page Freshness

Paper proof surface

Canonical route: /paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance

stale

Proof freshness: stale
Proof status: unverified
Display score: 5/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

OpenAlex: pending — this preprint is not yet indexed by OpenAlex.

Agent Handoff

Endpoint list, payload shape, route context, and copyable handoff data.

Agent Handoff

Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance

Canonical ID enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance | Route /paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance

MCP example

{
  "tool": "get_paper",
  "arguments": {
    "arxiv_id": "2602.10549"
  }
}

source_context

{
  "surface": "paper",
  "mode": "paper",
  "query": "Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance",
  "normalized_query": "2602.10549",
  "route": "/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance",
  "paper_ref": "enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Buildability Receipt

Verdict, compute envelope, blockers, signature state, and receipt links.

Paper proof page receipt window

Watch and verify: Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance

/buildability/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance

Watchwatch

Subject: Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Time to first demo

Insufficient data

No first-demo timestamp, owner estimate, or elapsed demo receipt is attached to this surface.

Compute envelope

Structured compute envelope

Insufficient data

No data, compute, hardware, memory, latency, dependency, or serving requirement receipt is attached.

Evidence ids

Receipt path

/buildability/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance

Paper ref

enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance

arXiv id

2602.10549

Freshness

Generated at

2026-04-02T02:30:40.136Z

Evidence freshness

stale

Last verification

2026-04-02T02:30:40.136Z

Sources

References

Coverage

17%

Hash state

Lineage hash

b4d6ccb4b5b2f7bfc2fe7bfad39b328bb73ec5b0d5bb3f2069f3e60d09237c65

Canonical opportunity-kernel lineage hash.

Signature state

External signature

unsigned_external

No founder, registry, pilot, or production-adoption signature is attached to this receipt.

Verification

not_verified

Verification is blocked until an external signature is provided.

Blockers

Missing: repo_url
Missing: references
Missing: proof_status
Missing: distribution_readiness_scores
Missing: paper_extraction_scorecards
Unknown: distribution readiness has not been computed yet
Unknown: proof verification has not been recorded yet

Verification pending / evidence receipt incomplete

repo_url

references

Missing proof, requirement, signature, approval, adoption, or telemetry fields are blockers and must not be inferred.

Open receipt API receipt Build Loop Signal Canvas Proof divergence Divergence API Brier outcomes API

Source Proof anchors

Visual citations from the paper document graph.

JSON-LD twin

The application/ld+json payload rendered for agents.

{
  "@context": "https://schema.org",
  "@graph": [
    {
      "@type": "WebPage",
      "@id": "https://sciencetostartup.com/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance#webpage",
      "url": "https://sciencetostartup.com/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance",
      "name": "Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance",
      "description": "Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.",
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      }
    },
    {
      "@type": "ScholarlyArticle",
      "@id": "https://sciencetostartup.com/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance#scholarlyArticle",
      "headline": "Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance",
      "description": "Leverage text-guided techniques to enhance multimodal video anomaly detection for reducing false alarms and improving anomaly characterization.",
      "url": "https://sciencetostartup.com/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance",
      "sameAs": "https://arxiv.org/abs/2602.10549",
      "identifier": {
        "@type": "PropertyValue",
        "propertyID": "arXiv",
        "value": "2602.10549"
      },
      "isAccessibleForFree": true,
      "isPartOf": {
        "@id": "https://sciencetostartup.com/#website"
      },
      "datePublished": "2026-02-11T05:44:30.000Z",
      "citation": [
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3492e6cefc1059f591c5a6f57349dd671231da0e"
          },
          "url": "https://www.semanticscholar.org/paper/3492e6cefc1059f591c5a6f57349dd671231da0e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a49c5891bf231b71de6f621df02d5ae803fbb9cb"
          },
          "url": "https://www.semanticscholar.org/paper/a49c5891bf231b71de6f621df02d5ae803fbb9cb"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "063942ed7474bb3a706f0e9f88ef1c6f4c43d886"
          },
          "url": "https://www.semanticscholar.org/paper/063942ed7474bb3a706f0e9f88ef1c6f4c43d886"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "53934efa1f572a12e93ecf664fbffe42fddf6468"
          },
          "url": "https://www.semanticscholar.org/paper/53934efa1f572a12e93ecf664fbffe42fddf6468"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "30a387f108243c89b28cb6a97f42c26052507995"
          },
          "url": "https://www.semanticscholar.org/paper/30a387f108243c89b28cb6a97f42c26052507995"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "86792c702a68d57fa72251b8dad3a70552638742"
          },
          "url": "https://www.semanticscholar.org/paper/86792c702a68d57fa72251b8dad3a70552638742"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "68fbbc67defe758bef7c10c9fba8703f10e17b24"
          },
          "url": "https://www.semanticscholar.org/paper/68fbbc67defe758bef7c10c9fba8703f10e17b24"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "a58a1eb932372f70039dbfb0b49af84de855d18e"
          },
          "url": "https://www.semanticscholar.org/paper/a58a1eb932372f70039dbfb0b49af84de855d18e"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "17a31a1e34d654913ec6834d8538ef8395254369"
          },
          "url": "https://www.semanticscholar.org/paper/17a31a1e34d654913ec6834d8538ef8395254369"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "503c37893318cf5ad5c39d2b32c8c05a60218905"
          },
          "url": "https://www.semanticscholar.org/paper/503c37893318cf5ad5c39d2b32c8c05a60218905"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "14765433d0636e73ae81a49dea4672fa585d4b3b"
          },
          "url": "https://www.semanticscholar.org/paper/14765433d0636e73ae81a49dea4672fa585d4b3b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0383e049e98c9eedbc61be728d4ef037300bbedf"
          },
          "url": "https://www.semanticscholar.org/paper/0383e049e98c9eedbc61be728d4ef037300bbedf"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0139e689add40a61c9454674edac4e93702aa5fc"
          },
          "url": "https://www.semanticscholar.org/paper/0139e689add40a61c9454674edac4e93702aa5fc"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "9e8cb8c91a0acb6e661b58ad724aa758490f2bea"
          },
          "url": "https://www.semanticscholar.org/paper/9e8cb8c91a0acb6e661b58ad724aa758490f2bea"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "14b68a8b869b52d3bcb8d8eae95f3b4e54aaa2dc"
          },
          "url": "https://www.semanticscholar.org/paper/14b68a8b869b52d3bcb8d8eae95f3b4e54aaa2dc"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "77c4f342a60dc403f37a28d2d969572a5fd1c11d"
          },
          "url": "https://www.semanticscholar.org/paper/77c4f342a60dc403f37a28d2d969572a5fd1c11d"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "6af5a5fab6d96e016b932ef8bb07e06e7820ecba"
          },
          "url": "https://www.semanticscholar.org/paper/6af5a5fab6d96e016b932ef8bb07e06e7820ecba"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "0938d0ccc1c633fa0f8c067d914358b1ef53a44b"
          },
          "url": "https://www.semanticscholar.org/paper/0938d0ccc1c633fa0f8c067d914358b1ef53a44b"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "965a0ff397ff33dbb9ee9a5b725472af4ffe0892"
          },
          "url": "https://www.semanticscholar.org/paper/965a0ff397ff33dbb9ee9a5b725472af4ffe0892"
        },
        {
          "@type": "ScholarlyArticle",
          "identifier": {
            "@type": "PropertyValue",
            "propertyID": "SemanticScholar",
            "value": "3f5b31c4f7350dc88002c121aecbdc82f86eb5bb"
          },
          "url": "https://www.semanticscholar.org/paper/3f5b31c4f7350dc88002c121aecbdc82f86eb5bb"
        }
      ],
      "additionalProperty": [
        {
          "@type": "PropertyValue",
          "propertyID": "viabilityScore",
          "value": 5
        },
        {
          "@type": "PropertyValue",
          "propertyID": "researchDomain",
          "value": "Video Surveillance AI"
        }
      ]
    },
    {
      "@type": "BreadcrumbList",
      "itemListElement": [
        {
          "@type": "ListItem",
          "position": 1,
          "name": "Home",
          "item": "https://sciencetostartup.com"
        },
        {
          "@type": "ListItem",
          "position": 2,
          "name": "Video Surveillance AI",
          "item": "https://sciencetostartup.com/topics"
        },
        {
          "@type": "ListItem",
          "position": 3,
          "name": "Enhancing Weakly Supervised Multimodal Video Anomaly Detecti",
          "item": "https://sciencetostartup.com/paper/enhancing-weakly-supervised-multimodal-video-anomaly-detection-through-text-guidance"
        }
      ]
    }
  ]
}

Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance

Enhancing Weakly Supervised Multimodal Video Anomaly Detection through Text Guidance

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(67)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

References(67)

Related Papers

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline