Papers
arxiv:2606.12985

Objects Before Words: Object-First Inductive Biases for Grounding Language in Child-View Video

Published on Jun 11
Authors:
,
,
,
,
,

Abstract

BabyMind uses object-first contrastive learning with mask-based extraction and tracking to resolve ambiguity in infant-view recordings for word learning under sparse supervision.

Learning grounded word meaning from natural experience requires resolving two ambiguities in infant-view recordings: when the named referent appears and where it is in a cluttered frame. In SAYCam-style data, caregiver speech is sparse and weakly synchronized with egocentric video, so single-frame contrastive pairing yields noisy positives in which the intended object is absent or entangled with distractors. We propose BabyMind, an object-first bias for child-view contrastive learning under sparse, noisy supervision. BabyMind extracts candidate object embeddings using an offline mask-based region interface, links candidates across a short utterance-centered window into lightweight object files via tracking, and aligns utterances to bags of object files with a prototype-space multiple-instance contrastive objective. Track-coherence and global-object agreement regularizers stabilize learning and transfer object-file structure into the global frame embedding used at evaluation. On SAYCam-S, BabyMind improves Labeled-S 15 forced-choice accuracy by +2.6 points over CVCL and yields consistent gains on in-vocabulary out-of-distribution benchmarks. Code is available at https://github.com/sathiiii/BabyMind.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.12985
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.12985 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.12985 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.