Skip to content
AI News HubLIVE
Original source2 min read

TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation

Summary

The paper argues that recurrent video slot-attention methods propagate slots unconditionally, causing state drift and decoder-induced reconstruction interference when objects are absent or occluded. It proposes Temporal Slot Activation (TSA), which learns per-slot, per-frame activation scores without visibility supervision and uses them to gate slot updates and decoder participation, with a Temporal Context Encoder for partial occlusion and gradual reappearance. TSA improves object decomposition and temporal identity preservation on MOVi-C/E, YT-VIS, and OVIS, with large gains on long, heavily occluded videos.

SourcearXiv Computer VisionAuthor: Duc Nguyen, Sieu Tran, Hao Vo, Khoa Vo, Duy Minh Ho Nguyen, Nghi D. Q. Bui, Anh Nguyen, Long Mai, Ngan Le
TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.13714] TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation

[Submitted on 10 Jun 2026]

Title:TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation

View a PDF of the paper titled TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation, by Duc Nguyen and 8 other authors

View PDF HTML (experimental)

Abstract:Unsupervised video object-centric learning aims to decompose dynamic scenes into temporally persistent entity representations. Existing recurrent video slot-attention methods propagate a fixed set of slots across frames, but typically assume unconditional slot propagation: every slot is updated and decoded at every frame, regardless of whether its corresponding object is visible. We show that this design violates a basic lifecycle requirement for persistent slots: when an object is absent or fully occluded, its slot should preserve its previous state and avoid explaining unrelated visible content. Instead, unconditional propagation creates two failure pathways: update-induced state drift, where current-frame evidence overwrites the absent object's representation, and decoder-induced reconstruction interference, where the inactive slot remains coupled to reconstruction through decoder attention. We propose Temporal Slot Activation (TSA), a mechanism that learns a per-slot, per-frame activation score $\alpha_{k,t} \in (0, 1)$ without visibility supervision. TSA uses this activation as a shared latent control variable for slot lifecycle modeling. When a slot is inactive, TSA anchors its state to the previous slot via activation-gated updating and suppresses its decoder participation through an activation-dependent additive bias on attention logits before softmax normalization. This jointly reduces state drift and reconstruction-driven interference. To improve decisions under partial occlusion and gradual reappearance, TSA further conditions activation prediction on a per-slot temporal memory produced by a Temporal Context Encoder. We evaluate TSA on MOVi-C/E, YT-VIS, and OVIS benchmarks using both standard and tracking-based metrics (FG-ARI, mBO, IDF1, HOTA). TSA consistently improves object decomposition and temporal identity preservation, with large gains on long, heavily occluded videos.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2606.13714 [cs.CV]

(or arXiv:2606.13714v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2606.13714

arXiv-issued DOI via DataCite

Submission history

From: Duc Nguyen [view email] [v1] Wed, 10 Jun 2026 20:54:45 UTC (16,566 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation, by Duc Nguyen and 8 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

ResearchersAdvanced

Key points

  • Identifies unconditional slot propagation as the cause of update-induced state drift and decoder-induced reconstruction interference
  • Learns per-slot, per-frame activation scores without visibility supervision as a shared latent control variable
  • Uses activation-gated updating and an additive attention-logit bias to suppress inactive slots in decoding
  • Improves FG-ARI, mBO, IDF1, and HOTA across benchmarks, especially on long, heavily occluded videos

Highlights and analysis are generated automatically and may contain errors. Check the original source.