paper-with-me

홈 › Papers

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

2026-06-11 · Sathira Silva, Abrham Kahsay Gebreselasie, Muhammad Umer Sheikh, Kartik Kuckreja, Daniel Harari, Muhammad Haris Khan arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.12985

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Similar Papers 제목 키워드 기반

Perceptual Inductive Bias Is What You Need Before Contrastive Learning

2025-01-01 · CVPR 2025 1 · Junru Zhao, Tianqin Li, Dunhan Jiang, Shenghao Wu 외

David Marr's seminal theory of human perception stipulates that visual processing is a multi-stage process, prioritizing the derivation of boundary and surface properties before forming semantic object representation…

Contrastive LearningDepth EstimationInductive BiasObject+3

Relational Graph Learning for Grounded Video Description Generation

2021-12-02 · Wenqiao Zhang, Xin Eric Wang, Siliang Tang, Haizhou Shi 외

Grounded video description (GVD) encourages captioning models to attend to appropriate video regions (e.g., objects) dynamically and generate a description. Such a setting can help explain the decisions of captioning mod…

Graph LearningHallucinationObjectObject Hallucination+1

CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally

2025-02-05 · Darina Koishigarina, Arnas Uselis, Seong Joon Oh

CLIP (Contrastive Language-Image Pretraining) has become a popular choice for various downstream tasks. However, recent studies have questioned its ability to represent compositional concepts effectively. These works sug…

Attributecross-modal alignment

A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications

2021-06-17 · Yun-Hao Cao, Jianxin Wu

This paper starts by revealing a surprising finding: without any learning, a randomly initialized CNN can localize objects surprisingly well. That is, a CNN has an inductive bias to naturally focus on objects, named as T…

Inductive BiasObjectobject-detectionObject Detection+1

Conditional Object-Centric Learning from Video

2021-11-24 · ICLR 2022 4 · Thomas Kipf, Gamaleldin F. Elsayed, Aravindh Mahendran, Austin Stone 외

Object-centric representations are a promising path toward more systematic generalization by providing flexible abstractions upon which compositional world models can be built. Recent work on simple 2D and 3D datasets ha…

3D geometryInstance SegmentationObjectOptical Flow Estimation+2