[Submitted on 10 Jun 2026 (v1), last revised 16 Oct 2026 (this version, v4)]
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 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 lightweight 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, MOVi-E, YTVIS-HQ, and the occlusion-heavy OVIS benchmarks, using standard (FG-ARI, mBO) and tracking-based (IDF1, HOTA) metrics. TSA improves object decomposition and temporal identity preservation, with large gains on long, heavily occluded videos.
Submission history
From: Duc Nguyen [view email]
[v1] Wed, 10 Jun 2026 20:54:45 UTC (16,566 KB)
[v2] Fri, 19 Jun 2026 17:52:18 UTC (16,564 KB)
[v3] Mon, 27 Jul 2026 19:26:04 UTC (16,559 KB)
[v4] Fri, 16 Oct 2026 02:28:34 UTC (15,406 KB)
