- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper studies complex aerial visual grounding, where an expression may refer to zero, one or multiple objects. The proposed HRVG uses a frozen Qwen3-8B to decompose each expression into scene-, entity- and relation-level fields. These fields guide three successive stages built on RemoteSAM and Grounding DINO: scene-conditioned encoder attention, entity-based candidate selection, and pairwise relation reasoning that scores each candidate and outputs a thresholded box set. The paper also introduces RefScene-20K, with 20,000 expressions over 8,550 VisDrone images covering relational, ordinal, extremal, multi-target and no-target cases. The expressions are generated by Qwen3-VL-32B and checked by geometric rules, a second VLM and human reviewers. HRVG reaches 59.87 / 60.95 Avg on RefScene-20K (Swin-T / Swin-B), about 5 points above the strongest baseline, and reports smaller gains on AerialVG and RefDrone.
Critical strengths
The paper targets an important difficulty in aerial grounding: compositional expressions involving scene context, relations, ordering, and variable target cardinality. The proposed benchmark RefScene-20K covers relational, ordinal, extremal, multi-target and no-target expressions in a unified setting. The results reveal that the ordinal track remains hard for all evaluated models.
Critical weaknesses
- The experiments do not yet support the paper's central claim that aligning semantic roles with visual stages drives the improvement. Ablation results are duplicated across tables (Table 3 and Table 5), and two variants described as removing different components report identical numbers on every metric. The variant with the largest drop (w/o PI) is described only conceptually, and it is unclear what it removes. The stage-reordering experiment is hard to interpret, because the three modules act on different parts of the architecture. Taken together, it is hard to verify that the reported ablations correspond to distinct trained models.
- The benchmark and the method are closely matched, and the comparison is not controlled. RefScene-20K expressions are generated from scene restrictions, attribute groups and relation or ordinal templates, which are the same fields the parser extracts. HRVG also uses a frozen 8B language model and a frozen RemoteSAM backbone that no baseline has access to, and no MLLM baseline is evaluated. On RefDrone, the gains over NGDINO are small. It is therefore hard to separate the benefit of hierarchical reasoning from the benefit of extra models and of a parse schema that matches how the data was generated.
Questions for authors
- Please clarify the benchmark taxonomy. Fig. 1 shows six expression types, but the statistics and Table 1 use only five tracks. Do the relational, ordinal and extremal tracks together make up the single-target expressions?
- Do , and correspond one-to-one to SGA, EGR and RGR? Is simply the candidate set in Eq. (7), or does it also pass dense visual features to the relation stage?
- What are the exact forms and loss weights of , and ?
- Tables 3 and 5 report exactly the same rows, and "w/o EGR" in Table 2 matches "w/o Entity Reasoning" in Table 3 on all six metrics. Yet the first removes a visual module and the second removes a text field. Are these distinct trained models? What exactly is removed in "w/o PI", given that Section 4.3 does not specify a separate inheritance mechanism?
- In Table 4, SGA acts on encoder attention, EGR on token alignment and RGR on candidate pairs, so their execution order is fixed by the architecture. What does an ordering such as Entity → Relation → Scene mean in practice? Are the text fields simply routed to different modules?
- RefScene-20K was generated with Qwen3-VL-32B, but no MLLM baseline is evaluated. How do fine-tuned MLLMs such as Qwen2.5-VL-7B or Qwen3-VL-8B perform on it? How does a Grounding DINO baseline perform if it receives the same parsed fields and applies rule-based ordinal or extremal selection over its boxes?
- Do the supervision targets for scene responses, directed relations, ordering and soft counts come from the RefScene-20K construction metadata, and if so, how is HRVG trained on AerialVG and RefDrone, where such metadata is not available?